Triple

T16543742
Position Surface form Disambiguated ID Type / Status
Subject Semi de Paris E401886 entity
Predicate abbreviation P43 FINISHED
Object Semi de Paris E401886 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: Semi de Paris | Statement: [Semi de Paris, abbreviation, Semi de Paris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Semi de Paris
Context triple: [Semi de Paris, abbreviation, Semi de Paris]
  • A. Semi de Paris chosen
    Semi de Paris is the popular annual half marathon race held in Paris, France, attracting tens of thousands of runners from around the world.
  • B. Rambuteau
    Rambuteau is a Paris Métro station located in the 3rd arrondissement near the Centre Pompidou and the historic Marais district.
  • C. Coupe de Ville
    Coupe de Ville is a 1990 American coming-of-age comedy-drama film about three estranged brothers who reconnect during a cross-country road trip in the 1960s.
  • D. Sixt-Fer-à-Cheval
    Sixt-Fer-à-Cheval is a picturesque alpine commune in the Haute-Savoie department of southeastern France, known for its dramatic cirque landscapes and mountain scenery.
  • E. duc de Tallard
    The duc de Tallard was a French noble title most notably held by Camille d’Hostun de la Baume, a prominent general and marshal of France during the late 17th and early 18th centuries.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3455fab34819086c77ff45b85f5db completed April 18, 2026, 8:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006ed9fa988190892ca20939080f5f completed May 10, 2026, 11:41 a.m.
Created at: April 10, 2026, 5:15 a.m.