Triple

T1963638
Position Surface form Disambiguated ID Type / Status
Subject Sherlock E42640 entity
Predicate createdBy P806 FINISHED
Object Mark Gatiss E218636 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: Mark Gatiss | Statement: [Sherlock, createdBy, Mark Gatiss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Gatiss
Context triple: [Sherlock, createdBy, Mark Gatiss]
  • A. Mark Gatiss chosen
    Mark Gatiss is a British actor, writer, and producer best known as a co-creator of the TV series "Sherlock" and for his work on "Doctor Who" and "The League of Gentlemen."
  • B. Stephen Merchant
    Stephen Merchant is an English comedian, writer, director, and actor best known as the co-creator of the acclaimed TV series "The Office" and frequent collaborator of Ricky Gervais.
  • C. Steven Moffat
    Steven Moffat is a Scottish television writer and producer best known for his work as showrunner on Doctor Who and co-creator of Sherlock.
  • D. Armando Iannucci
    Armando Iannucci is a Scottish satirist, writer, director, and producer best known for creating the political comedies "The Thick of It," "In the Loop," and HBO's "Veep."
  • E. Joseph Godber
    Joseph Godber was a British Conservative politician who held several senior government posts in the mid-20th century, including roles in agriculture and foreign affairs.
  • 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_69a88711151c8190940b2572095059d7 completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb3ac31a08190abaecac8badc52c7 completed March 7, 2026, 5:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae031ef4e48190af93dfd6f33184d3 completed March 8, 2026, 11:15 p.m.
Created at: March 4, 2026, 7:36 p.m.