Triple

T28174162
Position Surface form Disambiguated ID Type / Status
Subject Marcel Cachin E715543 entity
Predicate wasMemberOf P1168 FINISHED
Object French Communist Party Political Bureau
The French Communist Party Political Bureau was the party’s top leadership body, responsible for directing its political strategy and organizational decisions in France.
E35979 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: French Communist Party Political Bureau | Statement: [Marcel Cachin, wasMemberOf, French Communist Party Political Bureau]
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: French Communist Party Political Bureau
Triple: [Marcel Cachin, wasMemberOf, French Communist Party Political Bureau]
Generated description
The French Communist Party Political Bureau was the party’s top leadership body, responsible for directing its political strategy and organizational decisions in France.

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_69efd6b340f0819095680e15dcdc1830 completed April 27, 2026, 9:35 p.m.
NER Named-entity recognition batch_69f6423929c8819099c32e0a42b0cd4e completed May 2, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a15e6a9acf88190b4f833b819a283e3 completed May 26, 2026, 6:30 p.m.
NEDg Description generation batch_6a15e7567dc081908f4e671e88a88a57 completed May 26, 2026, 6:32 p.m.
NED2 Entity disambiguation (via description) batch_6a15e7d83f60819099641b792da90e90 completed May 26, 2026, 6:35 p.m.
Created at: April 27, 2026, 10:15 p.m.