Triple

T5623072
Position Surface form Disambiguated ID Type / Status
Subject Maria Maria E147652 entity
Predicate writer P1360 FINISHED
Object Wyclef Jean E60141 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: Wyclef Jean | Statement: [Maria Maria, writer, Wyclef Jean]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wyclef Jean
Context triple: [Maria Maria, writer, Wyclef Jean]
  • A. Wyclef Jean chosen
    Wyclef Jean is a Haitian-born rapper, musician, and producer best known as a member of the Fugees and for his successful solo career blending hip hop, reggae, and world music.
  • B. Warren G
    Warren G is an American West Coast rapper and producer best known for pioneering the G-funk sound and his hit single "Regulate."
  • C. Juelz Santana
    Juelz Santana is an American rapper from Harlem best known as a member of The Diplomats (Dipset) and for his early-2000s hits and collaborations in East Coast hip hop.
  • D. Talib Kweli
    Talib Kweli is an American rapper and activist known for his socially conscious lyrics and influential role in underground and alternative hip hop.
  • E. Raekwon
    Raekwon is an American rapper best known as a core member of the influential hip hop group Wu-Tang Clan and for his acclaimed solo album "Only Built 4 Cuban Linx...."
  • 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_69c00906f2a88190a992c66b13d606d4 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c02214b4948190b71a9f59499092f6 completed March 22, 2026, 5:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69c04d5da9cc819097281dd6aa405e62 completed March 22, 2026, 8:13 p.m.
Created at: March 22, 2026, 3:40 p.m.