Triple

T2852005
Position Surface form Disambiguated ID Type / Status
Subject Leonhard E63113 entity
Predicate relatedName P3889 FINISHED
Object Leon E79700 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: Leon | Statement: [Leonhard, relatedName, Leon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leon
Context triple: [Leonhard, relatedName, Leon]
  • A. Leon chosen
    Leon is a masculine given name of Greek origin meaning "lion," commonly used in various cultures worldwide.
  • B. Leo
    Leo is a zodiac constellation and astrological sign traditionally associated with the lion, symbolizing courage, leadership, and creativity.
  • C. Lewis
    "Lewis" is a notable film or television work featuring British actor Edward Fox, recognized as part of his distinguished acting career.
  • D. Lewis
    Lewis is a common English surname borne by numerous notable individuals across politics, civil rights, arts, and sports.
  • E. Mahon
    Mahon is a suburban area of Cork city in County Cork, Ireland, known for its residential estates, retail parks, and waterfront location on Cork Harbour.
  • 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_69ab4c407c408190857d25e027155ce9 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdf5ca2648190bd32c6ec4b0dd3b6 completed March 7, 2026, 8:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01d81e76c8190aae5e6dd9b13e28b completed March 10, 2026, 1:32 p.m.
Created at: March 6, 2026, 10:02 p.m.