Triple

T21487988
Position Surface form Disambiguated ID Type / Status
Subject Rectorat de Paris E530161 entity
Predicate collaboratesWith P37 FINISHED
Object Ville de Paris NE NERFINISHED

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: Ville de Paris | Statement: [Rectorat de Paris, collaboratesWith, Ville de Paris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ville de Paris
Context triple: [Rectorat de Paris, collaboratesWith, Ville de Paris]
  • A. Ville de Paris
    Ville de Paris was a prominent French ship of the line, originally the flagship of Admiral de Grasse, that played a central role in major naval engagements during the American Revolutionary War.
  • B. Ville de Paris chosen
    Ville de Paris is the municipal government and administrative authority responsible for managing and providing public services in the city of Paris, France.
  • C. Parigi
    Parigi is a coastal town that serves as the administrative center of Parigi Moutong Regency in Central Sulawesi, Indonesia.
  • D. Parigi
    Parigi is a town located in the Vikarabad district of the Indian state of Telangana.
  • E. Parisi
    Parisi is an Italian surname most notably associated with Giorgio Parisi, a Nobel Prize–winning theoretical physicist known for his work on complex systems and statistical mechanics.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c45acc3881908e38d3f28964152b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea390bd88190bc444e6af275f6e8 completed April 23, 2026, 9:45 a.m.
Created at: April 16, 2026, 6:22 p.m.