Triple

T19854950
Position Surface form Disambiguated ID Type / Status
Subject Esprit E477105 entity
Predicate hasBrand P1500 FINISHED
Object Esprit de Corp. 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: Esprit de Corp. | Statement: [Esprit, hasBrand, Esprit de Corp.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Esprit de Corp.
Context triple: [Esprit, hasBrand, Esprit de Corp.]
  • A. Esprit chosen
    Esprit is an international fashion brand known for its casual, contemporary clothing and lifestyle products.
  • B. Inter&Co
    Inter&Co is a Brazilian digital financial services company known for offering banking, investment, and insurance products through a unified online platform.
  • C. Terre des hommes
    Terre des hommes is a 1939 philosophical memoir by Antoine de Saint-Exupéry reflecting on aviation, humanism, and the meaning of human solidarity.
  • D. Spectra Fashions
    Spectra Fashions is a fictional, budget-conscious fashion house and longtime rival of Forrester Creations on the soap opera "The Bold and the Beautiful."
  • E. Lemaire
    Lemaire is a French surname borne by various notable figures in fields such as sports, politics, and the arts.
  • 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_69d8e51d39d081909bcfafeaaf3d2fcc completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6586b5b088190948ef002c1e77176 completed April 20, 2026, 4:46 p.m.
Created at: April 10, 2026, 1:51 p.m.