Triple

T2125768
Position Surface form Disambiguated ID Type / Status
Subject RAEng E46421 entity
Predicate awards P11 FINISHED
Object MacRobert Award E46418 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: MacRobert Award | Statement: [RAEng, awards, MacRobert Award]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MacRobert Award
Context triple: [RAEng, awards, MacRobert Award]
  • A. MacRobert Award chosen
    The MacRobert Award is a prestigious UK engineering prize recognizing outstanding innovation and commercial success in engineering.
  • B. Ellie Awards
    The Ellie Awards are prestigious annual honors recognizing excellence in American magazine journalism and publishing.
  • C. Crystal Award
    The Crystal Award is a World Economic Forum honor presented to artists and cultural leaders whose work has made a significant impact on improving the state of the world.
  • D. Clio Award
    The Clio Award is a prestigious international honor recognizing excellence and innovation in advertising and design across various media.
  • E. Phoenix Award
    The Phoenix Award is a literary prize that honors children's books of high quality that did not receive major recognition when they were first published.
  • 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_69a88a1626548190ae59a5028c3baa8e completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abbb57bc6881909f04a407beff33a6 completed March 7, 2026, 5:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae519ead088190a8a7229d998732de completed March 9, 2026, 4:50 a.m.
Created at: March 4, 2026, 7:44 p.m.