Triple

T7505189
Position Surface form Disambiguated ID Type / Status
Subject Shane Mosley E177368 entity
Predicate fought P30824 FINISHED
Object Manny Pacquiao E156320 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: Manny Pacquiao | Statement: [Shane Mosley, fought, Manny Pacquiao]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manny Pacquiao
Context triple: [Shane Mosley, fought, Manny Pacquiao]
  • A. Manny Pacquiao chosen
    Manny Pacquiao is a Filipino boxing legend and eight-division world champion widely regarded as one of the greatest professional boxers of all time.
  • B. Michael Pacquiao
    Michael Pacquiao is a Filipino rapper and public figure best known as the son of boxing legend and politician Manny Pacquiao.
  • C. Jimuel Pacquiao
    Jimuel Pacquiao is a Filipino amateur boxer and media personality best known as the eldest son of boxing legend and politician Manny Pacquiao.
  • D. Israel Pacquiao
    Israel Pacquiao is one of the sons of Filipino boxing legend and politician Manny Pacquiao.
  • E. Nonito Donaire
    Nonito Donaire is a Filipino professional boxer and multiple-time world champion known for his power, skill, and success across several weight divisions.
  • 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_69c69f2696688190915a8458f2398211 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f5b4c83c8190ace59f4d9e271904 completed March 27, 2026, 9:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83c9dcc2881908eea4efe075e894d completed March 28, 2026, 8:39 p.m.
Created at: March 27, 2026, 3:44 p.m.