Triple

T7762006
Position Surface form Disambiguated ID Type / Status
Subject Luna E176043 entity
Predicate hadTempleDedicatedTo P28305 FINISHED
Object Luna (Roman moon goddess) E111954 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: Luna (Roman moon goddess) | Statement: [Luna, hadTempleDedicatedTo, Luna (Roman moon goddess)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luna (Roman moon goddess)
Context triple: [Luna, hadTempleDedicatedTo, Luna (Roman moon goddess)]
  • A. Selene
    Selene is the tourist lunar excursion vehicle featured in Arthur C. Clarke’s science fiction novel "A Fall of Moondust."
  • B. Selene chosen
    Selene is the Greek goddess and personification of the Moon, often depicted driving a silver chariot across the night sky.
  • C. Luna
    Luna is a Spanish surname most prominently associated with Mexican actor and filmmaker Diego Luna.
  • D. Luna
    Luna is the natural satellite of Earth, renowned for its phases, influence on tides, and prominence in human culture and mythology.
  • E. Luna
    Luna was an ancient Roman town in northern Italy that served as a key urban and commercial center for the Ligurian region.
  • 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_69c69962923c8190ac74d28b4f9fe0a0 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c70404c2108190ad2b900ac9bf582b completed March 27, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8c7d658888190af97b83127086a2b completed March 29, 2026, 6:33 a.m.
Created at: March 27, 2026, 4:09 p.m.