Triple

T10418754
Position Surface form Disambiguated ID Type / Status
Subject Flora E245588 entity
Predicate residesAt P75 FINISHED
Object Bly E862354 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: Bly | Statement: [Flora, residesAt, Bly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bly
Context triple: [Flora, residesAt, Bly]
  • A. Bly chosen
    Bly is the remote English country estate that serves as the primary setting of Henry James's novella "The Turn of the Screw."
  • B. Harrow Hill
    Harrow Hill is a prominent elevated area in Harrow, London, known for its historic setting and association with the prestigious Harrow School.
  • C. Tono-Bungay
    Tono-Bungay is a 1909 novel by H. G. Wells that satirically explores capitalism, social change, and personal disillusionment through the rise and fall of a quack patent medicine empire.
  • D. Hailsham
    Hailsham is a market town in southeastern England known for its historic center and role as a local commercial hub within East Sussex.
  • E. Bakerville
    Bakerville is a small village within the town of New Hartford in Litchfield County, Connecticut.
  • 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_69d381be340c8190b05998703d42d224 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea2938188190a908316d0a0959be completed April 7, 2026, 11:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69d87e9b86648190b83eb5261c9a7b97 completed April 10, 2026, 4:37 a.m.
Created at: April 6, 2026, 12:11 p.m.