Triple

T9647910
Position Surface form Disambiguated ID Type / Status
Subject Alison Owen E233252 entity
Predicate child P120 FINISHED
Object Lily Allen E87106 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: Lily Allen | Statement: [Alison Owen, child, Lily Allen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lily Allen
Context triple: [Alison Owen, child, Lily Allen]
  • A. Lily Allen chosen
    Lily Allen is an English singer, songwriter, and author known for her sharp, witty lyrics and pop hits such as "Smile" and "The Fear."
  • B. Pixie Lott
    Pixie Lott is an English singer, songwriter, and actress who rose to fame with her 2009 debut single "Mama Do (Uh Oh, Uh Oh)" and subsequent pop hits.
  • C. Ellie Goulding
    Ellie Goulding is an English singer-songwriter known for her ethereal vocals and synth-pop hits such as "Lights" and "Love Me Like You Do."
  • D. Lydia Spelman
    Lydia Spelman was a member of the prominent Spelman family of Ohio, related to philanthropist Laura Spelman Rockefeller.
  • E. Sophie Ellis-Bextor
    Sophie Ellis-Bextor is an English singer and songwriter best known for her fusion of pop, disco, and electronic music, including hits like "Murder on the Dancefloor."
  • 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_69ca848b31648190b57aa55da20285be completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b826ff08190a972bdef84405f08 completed April 1, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1825dc8e08190bfc3475cd2e694ba completed April 4, 2026, 9:27 p.m.
Created at: March 30, 2026, 8:13 p.m.