Triple

T9648995
Position Surface form Disambiguated ID Type / Status
Subject Faye Dunaway E233284 entity
Predicate hasChild P369 FINISHED
Object Liam Dunaway O’Neill
Liam Dunaway O’Neill is the son of acclaimed American actress Faye Dunaway and photographer Terry O’Neill.
E811785 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: Liam Dunaway O’Neill | Statement: [Faye Dunaway, hasChild, Liam Dunaway O’Neill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liam Dunaway O’Neill
Context triple: [Faye Dunaway, hasChild, Liam Dunaway O’Neill]
  • A. Liam Sullivan
    Liam Sullivan was an American character actor known for his numerous television and film roles from the 1950s through the 1980s, often portraying suave or villainous figures.
  • B. Liam O’Connor
    Liam O’Connor is a British architect best known for designing prominent public memorials, including the Bomber Command Memorial in London.
  • C. Liam Lonergan
    Liam Lonergan is an Irish businessman best known as one of the founders of the low-cost airline Ryanair.
  • D. Luke Doolan
    Luke Doolan is an Australian film editor and filmmaker best known for his work on acclaimed films such as "Animal Kingdom."
  • E. Tim O'Connor
    Tim O'Connor is a New Zealand educational leader best known for serving as rector of the prestigious Auckland Grammar School.
  • 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: Liam Dunaway O’Neill
Triple: [Faye Dunaway, hasChild, Liam Dunaway O’Neill]
Generated description
Liam Dunaway O’Neill is the son of acclaimed American actress Faye Dunaway and photographer Terry O’Neill.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Liam Dunaway O’Neill
Target entity description: Liam Dunaway O’Neill is the son of acclaimed American actress Faye Dunaway and photographer Terry O’Neill.
  • A. Liam Sullivan
    Liam Sullivan was an American character actor known for his numerous television and film roles from the 1950s through the 1980s, often portraying suave or villainous figures.
  • B. Liam O’Connor
    Liam O’Connor is a British architect best known for designing prominent public memorials, including the Bomber Command Memorial in London.
  • C. Liam Lonergan
    Liam Lonergan is an Irish businessman best known as one of the founders of the low-cost airline Ryanair.
  • D. Luke Doolan
    Luke Doolan is an Australian film editor and filmmaker best known for his work on acclaimed films such as "Animal Kingdom."
  • E. Tim O'Connor
    Tim O'Connor is a New Zealand educational leader best known for serving as rector of the prestigious Auckland Grammar School.
  • 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_69ca848b31648190b57aa55da20285be completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9bac55b48190ab2a8f9bb83c951e completed April 1, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69d18262dc50819089cfc17c770a1a90 completed April 4, 2026, 9:28 p.m.
NEDg Description generation batch_69d183452244819080de72fda8e14e67 completed April 4, 2026, 9:31 p.m.
NED2 Entity disambiguation (via description) batch_69d183d506b881909375aadaaa616386 completed April 4, 2026, 9:34 p.m.
Created at: March 30, 2026, 8:13 p.m.