Triple

T20441607
Position Surface form Disambiguated ID Type / Status
Subject Heracles E501406 entity
Predicate child P120 FINISHED
Object Glenus 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: Glenus | Statement: [Heracles, child, Glenus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glenus
Context triple: [Heracles, child, Glenus]
  • A. Glenus chosen
    Glenus is a figure in Greek mythology known as a son of the hero Heracles and Deianira.
  • B. Steïr River
    The Steïr River is a small watercourse in Brittany, France, that flows through the city of Quimper before joining the Odet River.
  • C. Vils River
    The Vils River is a tributary waterway in the Alpine region of Austria and Germany that flows through scenic valleys before joining the Lech River.
  • D. Trient River
    The Trient River is a mountain river in the Swiss Alps that flows through the Trient Valley before joining the Rhône.
  • E. Glan River
    The Glan River is a watercourse in the Austrian state of Carinthia that flows through the city of Klagenfurt before joining the Gurk River.
  • 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_69e0b4ab3cfc8190ac9bf32e932316b1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e685f2e8888190a2e0d6b2bf6c905d completed April 20, 2026, 8 p.m.
Created at: April 16, 2026, 11:31 a.m.