Triple

T12574590
Position Surface form Disambiguated ID Type / Status
Subject David Haye E300172 entity
Predicate defeated P4779 FINISHED
Object Enzo Maccarinelli E992630 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: Enzo Maccarinelli | Statement: [David Haye, defeated, Enzo Maccarinelli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Enzo Maccarinelli
Context triple: [David Haye, defeated, Enzo Maccarinelli]
  • A. Enzo Maccarinelli chosen
    Enzo Maccarinelli is a Welsh former professional boxer and former WBO cruiserweight world champion known for his punching power.
  • B. Marco Mancini
    Marco Mancini is an Italian intelligence official known for his long career in Italy’s secret services and involvement in several high-profile national security cases.
  • C. Riccardo Lombardi
    Riccardo Lombardi was a prominent Italian socialist politician and intellectual, known for his leadership within the Italian Socialist Party and his advocacy of democratic socialism and progressive reforms in postwar Italy.
  • D. Gianluca Gregorini
    Gianluca Gregorini is the son of American actress and former model Barbara Bach.
  • E. Marco Leonardi
    Marco Leonardi is an Italian actor known for his roles in films such as "Cinema Paradiso," "Like Water for Chocolate," and various international productions.
  • 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_69d7bde87b648190bcd0266e9efde098 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954a629fc8190a1c3b6777aad4527 completed April 10, 2026, 7:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6686395c081909410b429fce6ebf8 completed May 2, 2026, 9:10 p.m.
Created at: April 9, 2026, 4:44 p.m.