Triple

T8207248
Position Surface form Disambiguated ID Type / Status
Subject Here Comes the Groom E191717 entity
Predicate screenwriter P2831 FINISHED
Object Liam O'Brien
Liam O'Brien was an American screenwriter and playwright known for his work on mid-20th-century Hollywood films and stage productions.
E719471 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 O'Brien | Statement: [Here Comes the Groom, screenwriter, Liam O'Brien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liam O'Brien
Context triple: [Here Comes the Groom, screenwriter, Liam O'Brien]
  • A. Liam O’Connor
    Liam O’Connor is a British architect best known for designing prominent public memorials, including the Bomber Command Memorial in London.
  • B. Dan O'Brien
    Dan O'Brien is a former American decathlete and Olympic gold medalist widely regarded as one of the greatest decathletes in history.
  • C. Liam O'Leary
    Liam O'Leary is a personal name that may refer to multiple individuals, typically of Irish origin, rather than a single widely recognized public figure.
  • D. Kevin O'Connell
    Kevin O'Connell is an American football coach and former NFL quarterback who serves as the head coach of the Minnesota Vikings.
  • E. Jay O’Connor
    Jay O’Connor is a child of John Jay O’Connor III, the husband of former U.S. Supreme Court Justice Sandra Day O’Connor.
  • 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 O'Brien
Triple: [Here Comes the Groom, screenwriter, Liam O'Brien]
Generated description
Liam O'Brien was an American screenwriter and playwright known for his work on mid-20th-century Hollywood films and stage productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Liam O'Brien
Target entity description: Liam O'Brien was an American screenwriter and playwright known for his work on mid-20th-century Hollywood films and stage productions.
  • A. Liam O’Connor
    Liam O’Connor is a British architect best known for designing prominent public memorials, including the Bomber Command Memorial in London.
  • B. Dan O'Brien
    Dan O'Brien is a former American decathlete and Olympic gold medalist widely regarded as one of the greatest decathletes in history.
  • C. Liam O'Leary
    Liam O'Leary is a personal name that may refer to multiple individuals, typically of Irish origin, rather than a single widely recognized public figure.
  • D. Kevin O'Connell
    Kevin O'Connell is an American football coach and former NFL quarterback who serves as the head coach of the Minnesota Vikings.
  • E. Jay O’Connor
    Jay O’Connor is a child of John Jay O’Connor III, the husband of former U.S. Supreme Court Justice Sandra Day O’Connor.
  • 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_69ca82c7f3e08190857bf1fc63b2a10c completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb726b520081908ce4a03bd14dfcdf completed March 31, 2026, 7:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccedda69148190b8c221221de5dae5 completed April 1, 2026, 10:05 a.m.
NEDg Description generation batch_69ccf1ba74548190831677bb126bea1a completed April 1, 2026, 10:21 a.m.
NED2 Entity disambiguation (via description) batch_69cd05c2059081908bd04ee4722f9aad completed April 1, 2026, 11:47 a.m.
Created at: March 30, 2026, 5:43 p.m.