Triple

T13831654
Position Surface form Disambiguated ID Type / Status
Subject Elementary E332411 entity
Predicate characterizesSherlockHolmesAs P111674 FINISHED
Object recovering drug addict LITERAL 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: recovering drug addict | Statement: [Elementary, characterizesSherlockHolmesAs, recovering drug addict]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: characterizesSherlockHolmesAs
Context triple: [Elementary, characterizesSherlockHolmesAs, recovering drug addict]
  • A. roleInSherlock
    Indicates the specific role or character that an entity portrays or holds in the context of the Sherlock series or franchise.
  • B. roleInMurderOnTheOrientExpress
    Indicates the specific involvement or function an entity has within the context of the murder case in "Murder on the Orient Express."
  • C. hasFictionalDetective
    Indicates that one entity (typically a work or series) features or includes a fictional detective character as part of its content.
  • D. workInSherlockHolmesCanon
    Indicates that an entity is a work (e.g., story, novel, adaptation) that belongs to or is part of the Sherlock Holmes canon.
  • E. relationshipWithSherlock
    Indicates that an entity has a specified type of personal or professional relationship with Sherlock.
  • F. None of above. chosen

Provenance (4 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_69d81c5ae7c88190b0dd41bdafeb5999 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0299334481908c2b271eaf06e4b7 completed April 14, 2026, 9:02 a.m.
PD Predicate disambiguation batch_69dbc86668e08190ba9135d1c3f38d35 completed April 12, 2026, 4:29 p.m.
PDg Predicate description generation batch_69dcad0eea9881908f71e1eed9a2446b completed April 13, 2026, 8:45 a.m.
Created at: April 9, 2026, 10:13 p.m.