Triple

T36111502
Position Surface form Disambiguated ID Type / Status
Subject Downton Abbey (estate) E1044509 entity
Predicate hasServantCharacters P4079 FINISHED
Object Mr. Carson NE NERFINISHED

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: Mr. Carson | Statement: [Downton Abbey (estate), hasServantCharacters, Mr. Carson]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasServantCharacters
Context triple: [Downton Abbey (estate), hasServantCharacters, Mr. Carson]
  • A. hasServant chosen
    Indicates that one entity has another entity serving it in a subordinate or attendant role.
  • B. notableServant
    Indicates that one entity serves another in a particularly distinguished, prominent, or historically significant capacity.
  • C. hasEnslavedCharacter
    Indicates that one entity has held another entity in a state of slavery or forced servitude.
  • D. hasPuppetCharacter
    Indicates that one entity features, includes, or is associated with a particular puppet character as part of its content or composition.
  • E. hasFairyCharacters
    Indicates that the subject includes or features characters that are fairies.
  • F. None of above.

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_69f76e344a4c8190af3858c6d78ba88f completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_6a0045a7b4c081908e4dedabda7cf790 completed May 10, 2026, 8:45 a.m.
PD Predicate disambiguation batch_6a0042b148a48190974b173f352e4b7f completed May 10, 2026, 8:32 a.m.
Created at: May 3, 2026, 4:08 p.m.