Triple

T3947967
Position Surface form Disambiguated ID Type / Status
Subject Paris Half Marathon E84791 entity
Predicate relatedEvent P37 FINISHED
Object Paris Marathon E386123 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: Paris Marathon | Statement: [Paris Half Marathon, relatedEvent, Paris Marathon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paris Marathon
Context triple: [Paris Half Marathon, relatedEvent, Paris Marathon]
  • A. Paris Marathon chosen
    The Paris Marathon is a major annual long-distance running race held in Paris, France, attracting tens of thousands of participants from around the world.
  • B. Berlin Marathon
    The Berlin Marathon is one of the world’s major city marathons, renowned for its flat, fast course where numerous marathon world records have been set.
  • C. Chicago Marathon
    The Chicago Marathon is one of the world’s premier annual long-distance running races, renowned for its flat, fast course through Chicago’s neighborhoods and its status as a major international marathon.
  • D. Marathón
    Marathón is a professional football club from Honduras, known as one of the country's most prominent and historically successful teams.
  • E. London Marathon
    The London Marathon is one of the world’s largest and most prestigious annual long-distance running events, held on the streets of London and attracting elite athletes and mass participants from around the globe.
  • 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_69aed934fbfc8190847068e4546de963 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef90f97188190875165e1b5f699e0 completed March 9, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5339bc5d481909e750873d65fff4c completed March 14, 2026, 10:08 a.m.
Created at: March 9, 2026, 3:30 p.m.