Triple

T3294016
Position Surface form Disambiguated ID Type / Status
Subject Gus E69166 entity
Predicate allyOf P4662 FINISHED
Object Jaq E62937 NE 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: Jaq | Statement: [Gus, allyOf, Jaq]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jaq
Context triple: [Gus, allyOf, Jaq]
  • A. Jaq chosen
    Jaq is one of Cinderella’s loyal mouse friends in Disney’s 1950 animated film, known for his bravery, resourcefulness, and comic personality.
  • B. Jaega
    The Jaega were a Native American people who inhabited the southeastern coast of Florida prior to European contact.
  • C. Tavros
    Tavros is a suburban municipality in the Athens urban area of Greece, known for its mixed residential and industrial character.
  • D. Rogil
    Rogil is a civil parish in the municipality of Aljezur in Portugal’s Algarve region, known for its rural landscape and Atlantic coastline.
  • E. Jerrik
    Jerrik is a masculine given name, likely a variant or cognate of names such as Eric, with similar Germanic roots and meaning.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ad859d45748190b0742408c954b39f completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb074f35081909dd3c8a09544b5f1 completed March 8, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2e86b8e04819091f4a4ae6d6a87ad completed March 12, 2026, 4:23 p.m.
Created at: March 8, 2026, 3:10 p.m.