Triple

T6732953
Position Surface form Disambiguated ID Type / Status
Subject ATB-EG E153680 entity
Predicate successor P78 FINISHED
Object ATB-NG
ATB-NG is a modernized successor to the ATB-EG system, designed as its next-generation iteration.
 E153680 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: ATB-NG | Statement: [ATB-EG, successor, ATB-NG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ATB-NG
Context triple: [ATB-EG, successor, ATB-NG]
  • A. ATB-EG
    ATB-EG is a Dutch train protection and signalling system used to control train speeds and enhance safety on the national railway network.
  • B. ABT
    ABT is the stock ticker symbol for Abbott Laboratories, a global healthcare company specializing in medical devices, diagnostics, nutrition products, and branded generic pharmaceuticals.
  • C. ABT
    ABT is a leading American classical ballet company renowned for its extensive repertoire and international tours.
  • D. ATN
    ATN most likely refers to Augmented Transition Network, a type of finite state machine used in computational linguistics and natural language processing for parsing sentences.
  • E. ANBG
    ANBG is the acronym for the Australian National Botanic Gardens, a major botanical institution in Canberra dedicated to the study, conservation, and display of Australia's native plant species.
  • 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: ATB-NG
Triple: [ATB-EG, successor, ATB-NG]
Generated description
ATB-NG is a modernized successor to the ATB-EG system, designed as its next-generation iteration.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ATB-NG
Target entity description: ATB-NG is a modernized successor to the ATB-EG system, designed as its next-generation iteration.
  • A. ATB-EG chosen
    ATB-EG is a Dutch train protection and signalling system used to control train speeds and enhance safety on the national railway network.
  • B. ABT
    ABT is the stock ticker symbol for Abbott Laboratories, a global healthcare company specializing in medical devices, diagnostics, nutrition products, and branded generic pharmaceuticals.
  • C. ABT
    ABT is a leading American classical ballet company renowned for its extensive repertoire and international tours.
  • D. ATN
    ATN most likely refers to Augmented Transition Network, a type of finite state machine used in computational linguistics and natural language processing for parsing sentences.
  • E. ANBG
    ANBG is the acronym for the Australian National Botanic Gardens, a major botanical institution in Canberra dedicated to the study, conservation, and display of Australia's native plant species.
  • F. None of above.

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_69c6880bdd68819097de8b6099992682 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d16ba51c81908dbf56b49d8360a8 completed March 27, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69c70b0502d081909662028e2b40c7f3 completed March 27, 2026, 10:56 p.m.
NEDg Description generation batch_69c70ba06a5c81909b65b52d21d37104 completed March 27, 2026, 10:58 p.m.
NED2 Entity disambiguation (via description) batch_69c70c755054819087d0db6f94d69eae completed March 27, 2026, 11:02 p.m.
Created at: March 27, 2026, 2:09 p.m.