Triple

T4543604
Position Surface form Disambiguated ID Type / Status
Subject The Dervish House E109993 entity
Predicate author P4 FINISHED
Object Ian McDonald E109993 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: Ian McDonald | Statement: [The Dervish House, author, Ian McDonald]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ian McDonald
Context triple: [The Dervish House, author, Ian McDonald]
  • A. Ian McDonald chosen
    Ian McDonald is a British science fiction author known for his richly imagined, culturally diverse speculative novels such as "River of Gods" and "Brasyl."
  • B. Stephen Baxter
    Stephen Baxter is a British science fiction author known for his hard science narratives, expansive space operas, and collaborations with Arthur C. Clarke.
  • C. Stephen Baxter
    Stephen Baxter is a Northern Irish football manager and former player best known for his long-term and highly successful tenure in charge of Crusaders FC.
  • D. M. John Harrison
    M. John Harrison is a British author renowned for his innovative and genre-defying science fiction, fantasy, and literary works such as the Viriconium series and "Light."
  • E. Charles Stross
    Charles Stross is a British science fiction and fantasy author known for his inventive, genre-blending works such as the "Laundry Files" and "Merchant Princes" series.
  • 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_69bd4412524c8190be5bcc9ddee91848 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57d517e881909c3d23ed4453b0a7 completed March 20, 2026, 2:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69bde06ca7f8819089305179ce52352d completed March 21, 2026, 12:03 a.m.
Created at: March 20, 2026, 1:05 p.m.