Triple

T15548144
Position Surface form Disambiguated ID Type / Status
Subject Tess Gallagher E370666 entity
Predicate givenName P17 FINISHED
Object Tess
Tess is the given name of American poet, essayist, and short story writer Tess Gallagher.
 E1163840 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: Tess | Statement: [Tess Gallagher, givenName, Tess]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tess
Context triple: [Tess Gallagher, givenName, Tess]
  • A. Tess
    Tess is a central character in the musical film "Burlesque," serving as the tough but caring owner and manager of the struggling burlesque club.
  • B. Tess
    Tess is a 1979 period drama film directed by Roman Polanski, adapted from Thomas Hardy’s novel "Tess of the d'Urbervilles."
  • C. Tess
    Tess is a character in the action film "Fast X," part of the long-running Fast & Furious franchise.
  • D. Tess
    Tess is a central angelic character from the television series "Touched by an Angel," known for her wise, no-nonsense guidance to both humans and fellow angels.
  • E. Tess
    Tess is a British television presenter and model best known for co-hosting the BBC One dance competition show "Strictly Come Dancing."
  • 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: Tess
Triple: [Tess Gallagher, givenName, Tess]
Generated description
Tess is the given name of American poet, essayist, and short story writer Tess Gallagher.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tess
Target entity description: Tess is the given name of American poet, essayist, and short story writer Tess Gallagher.
  • A. Tess
    Tess is a central character in the musical film "Burlesque," serving as the tough but caring owner and manager of the struggling burlesque club.
  • B. Tess
    Tess is a 1979 period drama film directed by Roman Polanski, adapted from Thomas Hardy’s novel "Tess of the d'Urbervilles."
  • C. Tess
    Tess is a character in the action film "Fast X," part of the long-running Fast & Furious franchise.
  • D. Tess
    Tess is a central angelic character from the television series "Touched by an Angel," known for her wise, no-nonsense guidance to both humans and fellow angels.
  • E. Tess
    Tess is a British television presenter and model best known for co-hosting the BBC One dance competition show "Strictly Come Dancing."
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a93121881909d88ca55a39252ac completed April 16, 2026, 2:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff455c172c8190833274cb98667e84 completed May 9, 2026, 2:31 p.m.
NEDg Description generation batch_69ff469e47fc819099d08f780ad81bf5 completed May 9, 2026, 2:37 p.m.
NED2 Entity disambiguation (via description) batch_69ff47aeddac8190a87024019ecb1396 completed May 9, 2026, 2:41 p.m.
Created at: April 10, 2026, 4:08 a.m.