Triple

T16946460
Position Surface form Disambiguated ID Type / Status
Subject Apis dorsata E411079 entity
Predicate combExposure P122308 FINISHED
Object exposed LITERAL 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: exposed | Statement: [Apis dorsata, combExposure, exposed]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: combExposure
Context triple: [Apis dorsata, combExposure, exposed]
  • A. nestExposure chosen
    Indicates that one entity is subjected to or experiences exposure related to a nest, such as environmental, observational, or risk-related contact with it.
  • B. exposes
    Indicates making something visible, known, or vulnerable by removing cover, concealment, or protection.
  • C. resultOfExposure
    Indicates that something occurs or exists as a consequence of being exposed to a particular agent, condition, or environment.
  • D. providesExposureTo
    Indicates that one entity gives another entity the opportunity to be seen, noticed, or become known by a particular audience, environment, or set of influences.
  • E. notableExposure
    Indicates that an entity has received significant public attention, visibility, or coverage, making it notably exposed or recognized.
  • F. None of above.

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_69d886c886688190967be07322597ac9 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3cfb25e0c8190948e62d9575ae9cd completed April 18, 2026, 6:38 p.m.
PD Predicate disambiguation batch_69e32b9aa8748190b248890aca86753d completed April 18, 2026, 6:58 a.m.
Created at: April 10, 2026, 5:31 a.m.