Triple

T7113280
Position Surface form Disambiguated ID Type / Status
Subject Parliament E165754 entity
Predicate hasVariant P455 FINISHED
Object Parliament Night Blue E165754 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: Parliament Night Blue | Statement: [Parliament, hasVariant, Parliament Night Blue]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parliament Night Blue
Context triple: [Parliament, hasVariant, Parliament Night Blue]
  • A. Butler Blue
    Butler Blue is the live English bulldog that serves as the beloved mascot of Butler University and its athletic teams.
  • B. Parliament chosen
    Parliament is a brand of cigarettes known for its recessed filter design and association with the tobacco company Philip Morris USA.
  • C. Parliament
    Parliament is the unicameral national legislature and supreme law-making body of Papua New Guinea.
  • D. Blue Police
    Blue Police was the colloquial name for the auxiliary police force composed largely of ethnic Poles that operated under German control in the General Government of occupied Poland during World War II.
  • E. Parlamentarium
    Parlamentarium is the European Parliament’s interactive visitors’ center in Brussels, offering multimedia exhibits about the EU’s history, institutions, and decision-making.
  • 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_69c6888120f081908f8f01b201dc4a4c completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e5ef813c8190bec0ab0cbae430e5 completed March 27, 2026, 8:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79cbc35d48190974e207eb98dcbe3 completed March 28, 2026, 9:17 a.m.
Created at: March 27, 2026, 2:43 p.m.