Triple

T14962586
Position Surface form Disambiguated ID Type / Status
Subject Rebel E373098 entity
Predicate starring P1507 FINISHED
Object Tamala Jones E148183 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: Tamala Jones | Statement: [Rebel, starring, Tamala Jones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tamala Jones
Context triple: [Rebel, starring, Tamala Jones]
  • A. Tamala Jones chosen
    Tamala Jones is an American actress known for her work in film and television, including prominent roles in romantic comedies and the TV series "Castle."
  • B. Tamala Edwards
    Tamala Edwards is an American journalist and television news anchor known for her work with ABC News and Philadelphia’s 6abc Action News.
  • C. Joy Denalane
    Joy Denalane is a German soul and R&B singer-songwriter known for blending neo-soul, jazz, and African musical influences in her work.
  • D. Kimberley Locke
    Kimberley Locke is an American singer, songwriter, and television personality who gained national recognition as a standout contestant on the second season of American Idol.
  • E. Keisha Castle-Hughes
    Keisha Castle-Hughes is a New Zealand actress best known for her Oscar-nominated breakthrough role in the film "Whale Rider" and later appearances in projects like "Game of Thrones."
  • 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_69d85cca979481908747d2a81eba1cea completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6d0487c8190b7754af8c5014b37 completed April 15, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe8bdeec408190893d1db9254da24e completed May 9, 2026, 1:20 a.m.
Created at: April 10, 2026, 2:40 a.m.