Triple

T11075236
Position Surface form Disambiguated ID Type / Status
Subject Hochtief E261848 entity
Predicate hasCompetitor P1375 FINISHED
Object Vinci E131991 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: Vinci | Statement: [Hochtief, hasCompetitor, Vinci]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vinci
Context triple: [Hochtief, hasCompetitor, Vinci]
  • A. Vinci
    Vinci is a small Tuscan town in Italy best known as the birthplace of Renaissance polymath Leonardo da Vinci.
  • B. Vinci chosen
    Vinci is a major French concessions and construction company and one of the largest infrastructure and engineering groups in the world.
  • C. Vinci Da
    Vinci Da is a Bengali psychological thriller film directed by Srijit Mukherji, centered on a make-up artist drawn into a series of morally complex crimes.
  • D. Viollet
    Viollet is a surname most notably associated with Dennis Viollet, an English footballer who starred for Manchester United in the 1950s.
  • E. Montech
    Montech is a small commune in southern France known for its historic canal infrastructure and rural charm within the Tarn-et-Garonne department.
  • 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_69d6aa9983c08190b0ef61603b69feac completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7994efb608190a81bc8c4d16ddbd0 completed April 9, 2026, 12:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c8cc77988190aad54f56dbd0f8cf completed April 18, 2026, 6:09 p.m.
Created at: April 8, 2026, 9:26 p.m.