Triple

T23143318
Position Surface form Disambiguated ID Type / Status
Subject Philippi Stadium E577519 entity
Predicate locatedIn P40 FINISHED
Object Philippi 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: Philippi | Statement: [Philippi Stadium, locatedIn, Philippi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philippi
Context triple: [Philippi Stadium, locatedIn, Philippi]
  • A. Philippi chosen
    Philippi is a township in Cape Town, South Africa, known as part of the Cape Flats area characterized by dense residential communities and socio-economic challenges.
  • B. Philippi
    Philippi was an ancient city in eastern Macedonia, notable in early Christianity as the site of one of the first European churches and a key location in the missionary journeys of the Apostle Paul.
  • C. Philippi
    Philippi is the abbreviated name of a 19th-century taxonomist who formally described and classified the species Margarites.
  • D. Colossae
    Colossae was an ancient Phrygian city in Asia Minor, notable in early Christianity as the community addressed by the New Testament Epistle to the Colossians.
  • E. Troas
    Troas is an ancient historical region in northwestern Asia Minor, near the Aegean coast, that included the legendary city of Troy.
  • 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_69e245f8e6248190ba3d58e068b4dccb completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18ecc3710819088ac5d72dad0459a completed April 29, 2026, 4:53 a.m.
Created at: April 17, 2026, 4 p.m.