Triple

T19335358
Position Surface form Disambiguated ID Type / Status
Subject Greysteel massacre E483607 entity
Predicate perpetrator P698 FINISHED
Object UDA 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: UDA | Statement: [Greysteel massacre, perpetrator, UDA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UDA
Context triple: [Greysteel massacre, perpetrator, UDA]
  • A. UDA chosen
    UDA is a loyalist paramilitary organization in Northern Ireland, formally known as the Ulster Defence Association, that was heavily involved in the Troubles.
  • B. UME
    UME is Spain’s specialized military emergency unit responsible for rapid response to natural disasters, major accidents, and other civil emergencies.
  • C. UCE
    UCE is a major public university in Quito, Ecuador, recognized as one of the country’s oldest and most important higher education institutions.
  • D. DU
    DU is a premier public central university in India, renowned for its diverse academic programs and large collegiate system based in New Delhi.
  • E. DU
    DU is the vehicle registration code used on license plates for the German city of Duisburg.
  • 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_69d8e8d13e3c81909d91d1d5ec37c095 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e61644b80c819080f9bca086424a36 completed April 20, 2026, 12:04 p.m.
Created at: April 10, 2026, 1:33 p.m.