Triple

T22999069
Position Surface form Disambiguated ID Type / Status
Subject Altair E572585 entity
Predicate otherComponentOf P150570 FINISHED
Object Vega 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: Vega | Statement: [Altair, otherComponentOf, Vega]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vega
Context triple: [Altair, otherComponentOf, Vega]
  • A. Vega
    Vega is a European small-lift launch vehicle developed by the European Space Agency and partners, primarily used to place light payloads into low Earth orbit.
  • B. Vega
    Vega is a Norwegian island renowned for its UNESCO-listed archipelago, traditional eiderdown harvesting, and rich coastal birdlife.
  • C. Vega
    Vega is an open-source visualization grammar and toolkit for creating, sharing, and exploring interactive data visualizations in a declarative JSON format.
  • D. Vega
    Vega is a masked, claw-wielding Spanish ninja and acrobatic antagonist from the Street Fighter fighting game series.
  • E. Vega chosen
    Vega is one of the brightest and most studied stars in the night sky, a nearby blue-white main-sequence star that serves as a key reference point in astronomy.
  • 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f182f54ce88190930530958e2a1830 completed April 29, 2026, 4:03 a.m.
Created at: April 17, 2026, 3:50 p.m.