Triple

T22520898
Position Surface form Disambiguated ID Type / Status
Subject Zoo Bioparco lake area E556770 entity
Predicate adjacentTo P224 FINISHED
Object Rome Zoo 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: Rome Zoo | Statement: [Zoo Bioparco lake area, adjacentTo, Rome Zoo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rome Zoo
Context triple: [Zoo Bioparco lake area, adjacentTo, Rome Zoo]
  • A. Bioparco di Roma chosen
    Bioparco di Roma is Rome’s historic zoological garden and major city zoo, located within the Villa Borghese park and home to a wide variety of animal species.
  • B. Hamura Zoo
    Hamura Zoo is a small, family-friendly zoological park in Hamura, Tokyo, known for its approachable scale and educational animal exhibits.
  • C. Varna Zoo
    Varna Zoo is a zoological park in the Bulgarian city of Varna, located within the popular seaside Sea Garden and featuring a variety of animal species for education and recreation.
  • D. Eberswalde Zoo
    Eberswalde Zoo is a regional zoological park in Eberswalde, Germany, known for its diverse animal collection and family-friendly natural setting.
  • E. Sóstó Zoo
    Sóstó Zoo is a major Hungarian zoological park in Nyíregyháza known for its extensive collection of animal species and immersive, naturalistic exhibits.
  • 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_69e11e5657e881909f16ca58352c50da completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15e31f43c8190899f5e35b150fe85 completed April 29, 2026, 1:26 a.m.
Created at: April 16, 2026, 8:50 p.m.