Triple

T16025771
Position Surface form Disambiguated ID Type / Status
Subject Skydra municipality E388713 entity
Predicate hasSeat P3522 FINISHED
Object Skydra E1189976 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: Skydra | Statement: [Skydra municipality, hasSeat, Skydra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Skydra
Context triple: [Skydra municipality, hasSeat, Skydra]
  • A. Skydra chosen
    Skydra is a town in northern Greece that serves as a local commercial and transportation hub within the Pella regional unit of Central Macedonia.
  • B. Aquilon
    Aquilon was a warship that engaged in naval combat with the British battleship HMS Goliath.
  • C. Stormfly
    Stormfly is Astrid Hofferson’s loyal Deadly Nadder dragon companion from the How to Train Your Dragon franchise.
  • D. Droshak
    Droshak is the official newspaper and central publication of the Armenian Revolutionary Federation, serving as a key organ for its political views and party news.
  • E. Taranis
    Taranis is a major Celtic thunder god often associated with the sky, storms, and the wheel as a symbol of his power.
  • 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_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1832790548190a74045d554e13328 completed April 17, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbcfd39c81909bfddfe95f9ad7d2 completed May 10, 2026, 1:13 a.m.
Created at: April 10, 2026, 4:55 a.m.