Triple

T23127778
Position Surface form Disambiguated ID Type / Status
Subject Phorcides E577079 entity
Predicate eyeSharedBy P2507 FINISHED
Object Pemphredo 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: Pemphredo | Statement: [Phorcides, eyeSharedBy, Pemphredo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pemphredo
Context triple: [Phorcides, eyeSharedBy, Pemphredo]
  • A. Pemphredo chosen
    Pemphredo is one of the three Graeae sisters from Greek mythology, ancient sea deities who shared a single eye and tooth among them.
  • B. Porpentina
    Porpentina is the full first name of Tina Goldstein, a witch and former Auror featured in J.K. Rowling’s Fantastic Beasts film series.
  • C. Phroso
    Phroso is an adventure novel by British author Anthony Hope, best known for its romantic intrigue and exotic Mediterranean island setting.
  • D. Zepho
    Zepho is a minor biblical figure mentioned in the Hebrew Bible as a descendant within the Edomite lineage.
  • E. Pervyse
    Pervyse is a village in West Flanders, Belgium, known for its location on the World War I Yser Front and the heavy fighting that took place there.
  • 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_69e245f7b0e481909c473ff4e6a54e2c completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18e55aa38819092816ffc52e20dbe completed April 29, 2026, 4:51 a.m.
Created at: April 17, 2026, 3:59 p.m.