Triple

T10435521
Position Surface form Disambiguated ID Type / Status
Subject Constance E246027 entity
Predicate hasVariant P455 FINISHED
Object Costanza E856901 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: Costanza | Statement: [Constance, hasVariant, Costanza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Costanza
Context triple: [Constance, hasVariant, Costanza]
  • A. Ludovica
    Ludovica is an Italian feminine given name, traditionally associated with nobility and derived from the same Germanic roots as names like Louise and Ludwig.
  • B. Guglielma
    Guglielma is an Italian feminine given name, serving as the female variant of Guglielmo (William).
  • C. Vittoria
    Vittoria is the Italian form of the name Victoria, commonly used as a female given name and place name in Italy.
  • D. Constanzia chosen
    Constanzia is the formal given name of Connie Corleone, the youngest child of Vito Corleone in Mario Puzo’s novel and the film series "The Godfather."
  • E. Adelaide del Vasto
    Adelaide del Vasto was a Norman noblewoman who served as regent of Sicily and later became queen consort of Jerusalem in the early 12th century.
  • 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_69d381bf3dc08190bf35a2643e4e8f22 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea843f1c8190afca4a42bc364468 completed April 7, 2026, 11:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69d87ec1a0908190b5369ad55cf2bcb1 completed April 10, 2026, 4:38 a.m.
Created at: April 6, 2026, 12:14 p.m.