Triple

T19669309
Position Surface form Disambiguated ID Type / Status
Subject Poison (song) E472289 entity
Predicate lyricist P1360 FINISHED
Object Bret Michaels 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: Bret Michaels | Statement: [Poison (song), lyricist, Bret Michaels]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bret Michaels
Context triple: [Poison (song), lyricist, Bret Michaels]
  • A. Bret Michaels chosen
    Bret Michaels is an American singer, songwriter, and reality television personality best known as the lead vocalist of the glam metal band Poison.
  • B. Gavin Rossdale
    Gavin Rossdale is a British musician best known as the lead singer and guitarist of the rock band Bush.
  • C. Nikki Sixx
    Nikki Sixx is an American musician, songwriter, and author best known as the co-founder and bassist of the heavy metal band Mötley Crüe.
  • D. Michael Sweet
    Michael Sweet is a software engineer best known as the original developer of the Common UNIX Printing System (CUPS), a widely used open-source printing system for Unix-like operating systems.
  • E. Sebastian Bach
    Sebastian Bach is a Canadian heavy metal singer best known as the former frontman of the band Skid Row.
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6416ad1b481908d2890d8c21aac5c completed April 20, 2026, 3:08 p.m.
Created at: April 10, 2026, 1:45 p.m.