Triple

T17165742
Position Surface form Disambiguated ID Type / Status
Subject Todd Manning E416602 entity
Predicate hasSister P31639 FINISHED
Object Tina Lord NE NERFINISHED

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: Tina Lord | Statement: [Todd Manning, hasSister, Tina Lord]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tina Lord
Context triple: [Todd Manning, hasSister, Tina Lord]
  • A. Tina Lord chosen
    Tina Lord is a fictional character from the soap opera "One Life to Live," known as Viki Lord's scheming and often trouble-prone sister.
  • B. Tina Landon
    Tina Landon is an acclaimed American choreographer best known for creating iconic dance routines for major pop artists and their music videos, including work with Janet Jackson, Rihanna, and Jennifer Lopez.
  • C. Toni Lawrence
    Toni Lawrence is an American actress known for her film and television work in the 1970s and 1980s.
  • D. Maria Tinney
    Maria Tinney is known as the child of American actress and writer Judy Lewis.
  • E. Tina Lawson
    Tina Lawson is an American fashion designer and businesswoman best known as the mother of singers Beyoncé and Solange Knowles and for designing many of Destiny’s Child’s early costumes.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d886d279c081909f8ff1f743ddeb69 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f914a0748190b2658edbe576ea2d completed April 18, 2026, 9:35 p.m.
Created at: April 10, 2026, 5:37 a.m.