Triple

T15451571
Position Surface form Disambiguated ID Type / Status
Subject Lyndall E371662 entity
Predicate hasSpellingVariant P457 FINISHED
Object Lyndal E371662 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: Lyndal | Statement: [Lyndall, hasSpellingVariant, Lyndal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lyndal
Context triple: [Lyndall, hasSpellingVariant, Lyndal]
  • A. Lyndall chosen
    Lyndall is a given name that can be used for people of any gender, often considered a variant or related form of the name Lyndon.
  • B. Lundigan
    Lundigan is a surname most notably associated with American film and television actor William Lundigan, who appeared in numerous movies and TV series from the 1930s through the 1960s.
  • C. Alness
    Alness is a small town in the Scottish Highlands, situated near the Cromarty Firth and known historically for its distilling and agricultural heritage.
  • D. Seafield
    Seafield is a small village in West Lothian, Scotland, known primarily as a residential community near the town of Livingston.
  • E. Haddo
    Haddo is a historic Scottish estate and country house associated with the Gordon family and the title of Lord Gordon of Haddo.
  • 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_69d85cc8bd308190886949510b42e764 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03efaf82c81908b464e37ce9c159a completed April 16, 2026, 1:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff21b1e9688190a283dbc552072ce0 completed May 9, 2026, 11:59 a.m.
Created at: April 10, 2026, 3:30 a.m.