Triple

T16009386
Position Surface form Disambiguated ID Type / Status
Subject Lyra Belacqua E388299 entity
Predicate givenName P17 FINISHED
Object Lyra E540387 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: Lyra | Statement: [Lyra Belacqua, givenName, Lyra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lyra
Context triple: [Lyra Belacqua, givenName, Lyra]
  • A. Lyra chosen
    Lyra is a small northern sky constellation best known for containing the bright star Vega and the Ring Nebula (M57).
  • B. Lyra Belacqua
    Lyra Belacqua is a brave, impulsive young girl from Philip Pullman’s His Dark Materials trilogy, known for her destiny-shaping role and her ability to read the alethiometer.
  • C. Lyra Angelica
    Lyra Angelica is a lyrical concerto for harp and string orchestra by British composer William Alwyn, admired for its romantic, expressive character.
  • D. Lyra the Sunshard
    Lyra the Sunshard is a legendary Priest minion in Hearthstone known for generating additional spells whenever you cast spells on your own turn.
  • E. Lyra Celtica
    Lyra Celtica is an influential late-19th-century anthology of Celtic poetry and song compiled by William Sharp (under the pseudonym Fiona Macleod), which helped popularize Celtic literary traditions in the English-speaking world.
  • 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_69d86dabcb7c8190b6a39d6831d2fa1b completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1828e9e708190aec0078913bf098a completed April 17, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbcc12dc8190a80d776b63a6ad35 completed May 10, 2026, 1:13 a.m.
Created at: April 10, 2026, 4:55 a.m.