Triple

T32559772
Position Surface form Disambiguated ID Type / Status
Subject The Adventures of Ford Fairlane E832189 entity
Predicate screenwriter P2831 FINISHED
Object James Cappe
James Cappe is a screenwriter best known for co-writing the 1990 action-comedy film "The Adventures of Ford Fairlane."
E2012355 NE FINISHED

How this triple was built (2 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: James Cappe | Statement: [The Adventures of Ford Fairlane, screenwriter, James Cappe]
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: James Cappe
Triple: [The Adventures of Ford Fairlane, screenwriter, James Cappe]
Generated description
James Cappe is a screenwriter best known for co-writing the 1990 action-comedy film "The Adventures of Ford Fairlane."

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_69f34926b9848190ace47d2dd0a0de7c completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6c6059f6481908d3e3ad74e5fca4d completed May 3, 2026, 3:50 a.m.
NED1 Entity disambiguation (via context triple) batch_6a347b93dc98819089e9f6803cd9c111 completed June 18, 2026, 11:13 p.m.
NEDg Description generation batch_6a347cdc6ec0819098a5621ff21b7059 completed June 18, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_6a347d818bf08190b03290203b8ad992 completed June 18, 2026, 11:21 p.m.
Created at: May 1, 2026, 1:03 a.m.