Triple

T1790591
Position Surface form Disambiguated ID Type / Status
Subject Invictus E39485 entity
Predicate cinematographyBy P1953 FINISHED
Object Tom Stern
Tom Stern is an American cinematographer best known for his frequent collaborations with director Clint Eastwood on numerous acclaimed films.
E203049 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: Tom Stern | Statement: [Invictus, cinematographyBy, Tom Stern]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Stern
Context triple: [Invictus, cinematographyBy, Tom Stern]
  • A. Jay Stern
    Jay Stern is a film producer best known for his work on mainstream Hollywood comedies, including the hit movie "Horrible Bosses."
  • B. Jeff Weltman
    Jeff Weltman is a basketball executive who serves as the top front-office decision-maker for the NBA’s Orlando Magic.
  • C. Andy Horwitz
    Andy Horwitz is a film producer best known for his work on major action and thriller projects in Hollywood.
  • D. Mark Stevens
    Mark Stevens was an American film and television actor best known for his roles in 1940s and 1950s dramas and film noir.
  • E. Rick Schnall
    Rick Schnall is an American private equity executive and sports investor best known as a principal owner of the NBA’s Charlotte Hornets.
  • 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: Tom Stern
Triple: [Invictus, cinematographyBy, Tom Stern]
Generated description
Tom Stern is an American cinematographer best known for his frequent collaborations with director Clint Eastwood on numerous acclaimed films.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tom Stern
Target entity description: Tom Stern is an American cinematographer best known for his frequent collaborations with director Clint Eastwood on numerous acclaimed films.
  • A. Jay Stern
    Jay Stern is a film producer best known for his work on mainstream Hollywood comedies, including the hit movie "Horrible Bosses."
  • B. Jeff Weltman
    Jeff Weltman is a basketball executive who serves as the top front-office decision-maker for the NBA’s Orlando Magic.
  • C. Andy Horwitz
    Andy Horwitz is a film producer best known for his work on major action and thriller projects in Hollywood.
  • D. Mark Stevens
    Mark Stevens was an American film and television actor best known for his roles in 1940s and 1950s dramas and film noir.
  • E. Rick Schnall
    Rick Schnall is an American private equity executive and sports investor best known as a principal owner of the NBA’s Charlotte Hornets.
  • 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa6512804c8190a5743c10bd37f83f completed March 6, 2026, 5:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69adbf54330c81908046b519a0297760 completed March 8, 2026, 6:26 p.m.
NEDg Description generation batch_69adbff135188190908058a2e2d41a1e completed March 8, 2026, 6:29 p.m.
NED2 Entity disambiguation (via description) batch_69adc0832cd881909702f380412702d5 completed March 8, 2026, 6:31 p.m.
Created at: March 4, 2026, 7:32 p.m.