Triple

T33497606
Position Surface form Disambiguated ID Type / Status
Subject Army of Shadows E857904 entity
Predicate castMember P1668 FINISHED
Object Claude Mann
Claude Mann is a French actor best known for his role in Jean-Pierre Melville’s acclaimed Resistance drama "Army of Shadows."
E2057135 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: Claude Mann | Statement: [Army of Shadows, castMember, Claude Mann]
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: Claude Mann
Triple: [Army of Shadows, castMember, Claude Mann]
Generated description
Claude Mann is a French actor best known for his role in Jean-Pierre Melville’s acclaimed Resistance drama "Army of Shadows."

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_69f3497660508190a541826a81f7e9ab completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6e56c04f081909d8303d2ec1c010d completed May 3, 2026, 6:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a35afc327e08190b62fc4059b49c254 completed June 19, 2026, 9:08 p.m.
NEDg Description generation batch_6a35b16322908190a5a690b8f266007c completed June 19, 2026, 9:15 p.m.
NED2 Entity disambiguation (via description) batch_6a35b1d9c7b48190ab188ad30885a9e4 completed June 19, 2026, 9:17 p.m.
Created at: May 1, 2026, 1:38 a.m.