Triple

T22172308
Position Surface form Disambiguated ID Type / Status
Subject The Window E547952 entity
Predicate mainCharacter P1183 FINISHED
Object Tommy Woodry
Tommy Woodry is the young boy protagonist of the 1949 film noir "The Window," whose eyewitness account of a crime drives the suspenseful plot.
E1524159 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: Tommy Woodry | Statement: [The Window, mainCharacter, Tommy Woodry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tommy Woodry
Context triple: [The Window, mainCharacter, Tommy Woodry]
  • A. Sherman Kell
    Sherman Kell is a film editor known for his work on the classic silent comedy "The Cameraman."
  • B. Jim McClain
    Jim McClain is a writer known for creating the story for the work titled "Robots."
  • C. Todd Duffey
    Todd Duffey is an American actor best known for playing the overenthusiastic waiter Brian in the cult comedy film "Office Space."
  • D. Tommy Tilden
    Tommy Tilden is a small-town coroner and widowed father who becomes entangled in a terrifying supernatural mystery while performing an autopsy in the horror film "The Autopsy of Jane Doe."
  • E. Hank McCamish
    Hank McCamish was a prominent Atlanta insurance executive and philanthropist whose support for Georgia Tech athletics led to the university’s basketball arena being named in his honor.
  • 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: Tommy Woodry
Triple: [The Window, mainCharacter, Tommy Woodry]
Generated description
Tommy Woodry is the young boy protagonist of the 1949 film noir "The Window," whose eyewitness account of a crime drives the suspenseful plot.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tommy Woodry
Target entity description: Tommy Woodry is the young boy protagonist of the 1949 film noir "The Window," whose eyewitness account of a crime drives the suspenseful plot.
  • A. Sherman Kell
    Sherman Kell is a film editor known for his work on the classic silent comedy "The Cameraman."
  • B. Jim McClain
    Jim McClain is a writer known for creating the story for the work titled "Robots."
  • C. Todd Duffey
    Todd Duffey is an American actor best known for playing the overenthusiastic waiter Brian in the cult comedy film "Office Space."
  • D. Tommy Tilden
    Tommy Tilden is a small-town coroner and widowed father who becomes entangled in a terrifying supernatural mystery while performing an autopsy in the horror film "The Autopsy of Jane Doe."
  • E. Hank McCamish
    Hank McCamish was a prominent Atlanta insurance executive and philanthropist whose support for Georgia Tech athletics led to the university’s basketball arena being named in his honor.
  • 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_69e11e3d53f88190a2b690e3f25bb062 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12a69c12c8190a03177b5b740456a completed April 28, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0aa606177081908b30cff5514cd8c7 completed May 18, 2026, 5:39 a.m.
NEDg Description generation batch_6a0aa754e2f08190ad4b2186ab0994b3 completed May 18, 2026, 5:44 a.m.
NED2 Entity disambiguation (via description) batch_6a0aa79ada5881908b6a6a86290f119e completed May 18, 2026, 5:46 a.m.
Created at: April 16, 2026, 8:34 p.m.