Triple

T524243
Position Surface form Disambiguated ID Type / Status
Subject Girl on Fire E10882 entity
Predicate producer P490 FINISHED
Object Salaam Remi E65202 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: Salaam Remi | Statement: [Girl on Fire, producer, Salaam Remi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salaam Remi
Context triple: [Girl on Fire, producer, Salaam Remi]
  • A. Salaam Remi chosen
    Salaam Remi is an American record producer and songwriter best known for his work with artists like Amy Winehouse, Nas, and the Fugees, blending hip-hop, reggae, and soul influences.
  • B. Rafi
    Rafi was an Israeli political party founded by David Ben-Gurion in the 1960s after a split from Mapai, known for its activist and security-focused policies.
  • C. Sami
    Sami is a group of indigenous Uralic languages spoken by the Sámi people across northern parts of Norway, Sweden, Finland, and Russia.
  • D. Malik
    Malik is a common Arabic surname and given name used across various cultures, often meaning "king" or "owner."
  • E. Ali
    "Ali" is a biographical sports drama film about boxer Muhammad Ali, noted for Emmanuel Lubezki’s distinctive cinematography.
  • 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_69a2e84b16c4819088d284c47c3a7968 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f1b656c08190b387f21b06d99e68 completed Feb. 28, 2026, 1:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4b5d50c688190b0093af8870f6fdf completed March 1, 2026, 9:55 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.