Triple
T5201141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Body Heat |
E117394
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
Matty Walker
Matty Walker is the seductive and manipulative femme fatale at the center of the neo-noir film "Body Heat."
|
E502378
|
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: Matty Walker | Statement: [Body Heat, mainCharacter, Matty Walker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matty Walker Context triple: [Body Heat, mainCharacter, Matty Walker]
-
A.
Rob Walker
Rob Walker is a technology entrepreneur best known as a co-founder of the semiconductor company LSI Logic.
-
B.
James Walker
James Walker was a prominent 19th-century British civil engineer known for his influential role in advancing the profession and shaping major infrastructure projects in the United Kingdom.
-
C.
Matt Walker
Matt Walker is the son of former Wisconsin governor and Republican politician Scott Walker.
-
D.
Garrett Walker
Garrett Walker is the fictional President of the United States in the political drama series "House of Cards," whose administration becomes entangled in the ruthless schemes of Frank Underwood.
-
E.
Roy Walker
Roy Walker is the injured Hollywood stuntman whose fantastical storytelling to a young girl drives the narrative of the 2006 film "The Fall."
- 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: Matty Walker Triple: [Body Heat, mainCharacter, Matty Walker]
Generated description
Matty Walker is the seductive and manipulative femme fatale at the center of the neo-noir film "Body Heat."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Matty Walker Target entity description: Matty Walker is the seductive and manipulative femme fatale at the center of the neo-noir film "Body Heat."
-
A.
Rob Walker
Rob Walker is a technology entrepreneur best known as a co-founder of the semiconductor company LSI Logic.
-
B.
James Walker
James Walker was a prominent 19th-century British civil engineer known for his influential role in advancing the profession and shaping major infrastructure projects in the United Kingdom.
-
C.
Matt Walker
Matt Walker is the son of former Wisconsin governor and Republican politician Scott Walker.
-
D.
Garrett Walker
Garrett Walker is the fictional President of the United States in the political drama series "House of Cards," whose administration becomes entangled in the ruthless schemes of Frank Underwood.
-
E.
Roy Walker
Roy Walker is the injured Hollywood stuntman whose fantastical storytelling to a young girl drives the narrative of the 2006 film "The Fall."
- 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_69bd4463dd3c81909966123f20b79d57 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7a228e2c81908bfbd48ed9f2cd5e |
completed | March 20, 2026, 4:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bee0a6698c81908cc1fc7c15ffa5b7 |
completed | March 21, 2026, 6:17 p.m. |
| NEDg | Description generation | batch_69bee6cf3fd08190802ddba139a682c6 |
completed | March 21, 2026, 6:43 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69beea9b7eec8190b6fb2b402398a33d |
completed | March 21, 2026, 6:59 p.m. |
Created at: March 20, 2026, 1:47 p.m.