Triple

T12851147
Position Surface form Disambiguated ID Type / Status
Subject John Lawrence, 2nd Baron Lawrence E307320 entity
Predicate style P87 FINISHED
Object Lord Lawrence E1002748 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: Lord Lawrence | Statement: [John Lawrence, 2nd Baron Lawrence, style, Lord Lawrence]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lord Lawrence
Context triple: [John Lawrence, 2nd Baron Lawrence, style, Lord Lawrence]
  • A. Lord Lawrence chosen
    Lord Lawrence is a noble title in the British peerage associated with the Barony of Lawrence.
  • B. Lord Holland
    Lord Holland was a prominent British Whig politician and statesman of the 19th century, known for his influence in liberal reform and his role in successive governments.
  • C. Colonel Brighton
    Colonel Brighton is a British military officer character in the film "Lawrence of Arabia," serving as a liaison between T.E. Lawrence and the British command.
  • D. Lord Douglas
    Lord Douglas is a Scottish peerage title historically associated with the influential Douglas family and their estates in Kilmount, Middlebie, and Dornock.
  • E. Lord Hill
    Lord Hill was a British nobleman whose title is commemorated in various place names, including Lord Hill Regional Park in Washington State.
  • 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_69d7bdf5e7cc8190be357278bc5ba3bb completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97020eacc81909357b3398d17dc49 completed April 10, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f69ba5059c81908be3b8b371518f41 completed May 3, 2026, 12:49 a.m.
Created at: April 9, 2026, 5:36 p.m.