Triple

T8394869
Position Surface form Disambiguated ID Type / Status
Subject Madeline Usher E198028 entity
Predicate familyName P18 FINISHED
Object Usher E64985 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: Usher | Statement: [Madeline Usher, familyName, Usher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Usher
Context triple: [Madeline Usher, familyName, Usher]
  • A. Usher chosen
    Usher is an American R&B singer, songwriter, dancer, and actor known for his smooth vocals, dynamic performances, and multi-platinum albums such as "Confessions."
  • B. Usher II
    Usher II is a short story by Ray Bradbury, set on Mars, that satirizes censorship and pays homage to Edgar Allan Poe within the larger collection The Martian Chronicles.
  • C. Ne-Yo
    Ne-Yo is an American R&B singer, songwriter, and record producer known for hits like "So Sick" and for writing songs for numerous major artists.
  • D. Marques Houston
    Marques Houston is an American R&B singer, songwriter, and actor best known as a member of the group Immature/IMx and for his roles in television and film.
  • E. Chris Brown
    Chris Brown is a film producer known for his work on the World War II drama "The Railway Man."
  • 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_69ca82f816bc8190ab321c07d72208c1 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb8185ef60819085cfa7491d35834a completed March 31, 2026, 8:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde85ee7b08190bfbcbed0edb142dd completed April 2, 2026, 3:54 a.m.
Created at: March 30, 2026, 6:03 p.m.