Triple

T8993081
Position Surface form Disambiguated ID Type / Status
Subject Elmo E214835 entity
Predicate publishedAtConference P21395 FINISHED
Object NAACL 2018
NAACL 2018 was a major computational linguistics conference where the influential ELMo deep contextualized word representation model was introduced.
 E771679 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: NAACL 2018 | Statement: [Elmo, publishedAtConference, NAACL 2018]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: NAACL 2018
Context triple: [Elmo, publishedAtConference, NAACL 2018]
  • A. EMNLP
    EMNLP (Empirical Methods in Natural Language Processing) is a leading annual conference in computational linguistics and natural language processing research.
  • B. ACM Transactions on Asian and Low-Resource Language Information Processing
    ACM Transactions on Asian and Low-Resource Language Information Processing is a peer-reviewed scholarly journal focusing on computational linguistics, natural language processing, and information processing for Asian and other low-resource languages.
  • C. NeurIPS
    NeurIPS is a premier international conference focused on advances in machine learning, artificial intelligence, and computational neuroscience.
  • D. TACL
    TACL (Transactions of the Association for Computational Linguistics) is a leading peer-reviewed journal publishing high-quality research in natural language processing and computational linguistics.
  • E. “A Computer Program for Understanding Natural Language”
    “A Computer Program for Understanding Natural Language” is a landmark 1968 paper by Terry Winograd that presents an early natural language understanding system capable of interpreting and executing commands in a simulated blocks world.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: NAACL 2018
Triple: [Elmo, publishedAtConference, NAACL 2018]
Generated description
NAACL 2018 was a major computational linguistics conference where the influential ELMo deep contextualized word representation model was introduced.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: NAACL 2018
Target entity description: NAACL 2018 was a major computational linguistics conference where the influential ELMo deep contextualized word representation model was introduced.
  • A. EMNLP
    EMNLP (Empirical Methods in Natural Language Processing) is a leading annual conference in computational linguistics and natural language processing research.
  • B. ACM Transactions on Asian and Low-Resource Language Information Processing
    ACM Transactions on Asian and Low-Resource Language Information Processing is a peer-reviewed scholarly journal focusing on computational linguistics, natural language processing, and information processing for Asian and other low-resource languages.
  • C. NeurIPS
    NeurIPS is a premier international conference focused on advances in machine learning, artificial intelligence, and computational neuroscience.
  • D. TACL
    TACL (Transactions of the Association for Computational Linguistics) is a leading peer-reviewed journal publishing high-quality research in natural language processing and computational linguistics.
  • E. “A Computer Program for Understanding Natural Language”
    “A Computer Program for Understanding Natural Language” is a landmark 1968 paper by Terry Winograd that presents an early natural language understanding system capable of interpreting and executing commands in a simulated blocks world.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ca83a05c608190bdfdbdb25e994b39 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6876583081909d936dc3c3152587 completed April 1, 2026, 12:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0cd2b948190947a26fe11ad81bf completed April 3, 2026, 2:38 p.m.
NEDg Description generation batch_69cfd27680408190a5ebcebacf9e4303 completed April 3, 2026, 2:45 p.m.
NED2 Entity disambiguation (via description) batch_69cfd2dbf3cc81909589bd9467239573 completed April 3, 2026, 2:46 p.m.
Created at: March 30, 2026, 7:04 p.m.