Triple

T11711008
Position Surface form Disambiguated ID Type / Status
Subject Carla Bruni E278372 entity
Predicate familyName P18 FINISHED
Object Bruni E302249 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: Bruni | Statement: [Carla Bruni, familyName, Bruni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bruni
Context triple: [Carla Bruni, familyName, Bruni]
  • A. Bruni chosen
    Bruni is a surname most notably associated with Fyodor Bruni, a 19th-century Russian-Italian painter known for his historical and religious works.
  • B. Gabrieletta
    Gabrieletta is an Italian feminine diminutive given name derived from Gabriele, typically conveying affection or smallness.
  • C. Piermarini
    Piermarini is an Italian surname most notably associated with Giuseppe Piermarini, an 18th-century architect renowned for designing Milan’s Teatro alla Scala.
  • D. Braschi
    Braschi is the Italian noble family from which Pope Pius VI originated.
  • E. Doncello
    Doncello is a municipality located in the Caquetá Department of southern Colombia, known for its agricultural activities and position within the Amazonian foothills.
  • 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_69d6aaff2ce88190b4a1e4b341ad5377 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a49f072c81909c6a964a92e5bc0c completed April 10, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef8374e6cc8190bba7f2f3ca6f4de9 completed April 27, 2026, 3:40 p.m.
Created at: April 8, 2026, 9:40 p.m.