Triple

T17432408
Position Surface form Disambiguated ID Type / Status
Subject Edith Cowan University E423905 entity
Predicate abbreviation P43 FINISHED
Object ECU 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: ECU | Statement: [Edith Cowan University, abbreviation, ECU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ECU
Context triple: [Edith Cowan University, abbreviation, ECU]
  • A. ECU
    ECU is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Ecuador in international standards and data systems.
  • B. ECU chosen
    ECU is a public Australian university based in Perth, Western Australia, named after social reformer Edith Cowan and known for its teaching and research across a wide range of disciplines.
  • C. ECU
    ECU is a public research university in Greenville, North Carolina, known for its comprehensive academic programs and strong emphasis on health sciences and regional engagement.
  • D. ECUs (electronic control units)
    ECUs (electronic control units) are embedded automotive computers that monitor and control various vehicle systems such as engine performance, safety features, and comfort functions.
  • E. ECan
    ECan is the regional council responsible for environmental management and resource planning in the Canterbury region of New Zealand.
  • 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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e449014b388190ba8c9023d3c9dd99 completed April 19, 2026, 3:16 a.m.
Created at: April 10, 2026, 5:46 a.m.