Triple

T20474953
Position Surface form Disambiguated ID Type / Status
Subject William Ashley Sunday E502290 entity
Predicate familyName P18 FINISHED
Object Sunday 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: Sunday | Statement: [William Ashley Sunday, familyName, Sunday]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sunday
Context triple: [William Ashley Sunday, familyName, Sunday]
  • A. Sunday
    Sunday is the first day of the week in many cultures, widely recognized in Christianity as a principal day of worship and rest.
  • B. Saturday
    "Saturday" is a follow-up pop song by Rebecca Black that playfully reflects on and responds to the viral fame of her earlier hit "Friday."
  • C. Saturday
    "Saturday" is a 2005 novel by Ian McEwan that follows a neurosurgeon through a single, tension-filled day in London, exploring themes of post-9/11 anxiety, morality, and personal responsibility.
  • D. Sunday Sun
    "Sunday Sun" is a song by Beck from his critically acclaimed 2002 album *Sea Change*, known for its melancholic, introspective style.
  • E. Domenica chosen
    Domenica is a feminine given name of Latin origin meaning "belonging to the Lord" or "born on Sunday."
  • 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_69e0b4ae5f1081908768b0c9a3a0bf38 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6996464448190bdf9cf63c736d6dd completed April 20, 2026, 9:23 p.m.
Created at: April 16, 2026, 11:34 a.m.