Triple

T1225038
Position Surface form Disambiguated ID Type / Status
Subject David H. Souter E26307 entity
Predicate familyName P18 FINISHED
Object Souter
Souter is a surname most prominently associated with David H. Souter, a former Associate Justice of the United States Supreme Court.
 E139410 NE FINISHED

How this triple was built (4 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: Souter | Statement: [David H. Souter, familyName, Souter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Souter
Context triple: [David H. Souter, familyName, Souter]
  • A. Southery
    Southery is a village and civil parish in Norfolk, England, situated in the Fens near the River Great Ouse.
  • B. Sutherland
    Sutherland is a small town in the Northern Cape province of South Africa, best known for its exceptionally clear night skies and major astronomical observatories.
  • C. Hannington
    Hannington is a small rural village in Wiltshire, England, known for its traditional English countryside setting and historic character.
  • D. Ledeacker
    Ledeacker is a small village in the Dutch province of North Brabant, now part of the municipality of Land van Cuijk.
  • E. Robnett
    Robnett is a given middle name that appears in the full name of individuals such as the American politician and jurist James Lick Robnett.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Souter
Triple: [David H. Souter, familyName, Souter]
Generated description
Souter is a surname most prominently associated with David H. Souter, a former Associate Justice of the United States Supreme Court.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Souter
Target entity description: Souter is a surname most prominently associated with David H. Souter, a former Associate Justice of the United States Supreme Court.
  • A. Southery
    Southery is a village and civil parish in Norfolk, England, situated in the Fens near the River Great Ouse.
  • B. Sutherland
    Sutherland is a small town in the Northern Cape province of South Africa, best known for its exceptionally clear night skies and major astronomical observatories.
  • C. Hannington
    Hannington is a small rural village in Wiltshire, England, known for its traditional English countryside setting and historic character.
  • D. Ledeacker
    Ledeacker is a small village in the Dutch province of North Brabant, now part of the municipality of Land van Cuijk.
  • E. Robnett
    Robnett is a given middle name that appears in the full name of individuals such as the American politician and jurist James Lick Robnett.
  • F. None of above. chosen

Provenance (5 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_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be382c4081909238c18b805352a7 completed March 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac832704c08190a1a73ebd90fa91b8 completed March 7, 2026, 7:57 p.m.
NEDg Description generation batch_69ac83add3608190be198ba153721d5c completed March 7, 2026, 7:59 p.m.
NED2 Entity disambiguation (via description) batch_69ac846e724081909696c8c44f2f9500 completed March 7, 2026, 8:02 p.m.
Created at: March 1, 2026, 7:47 p.m.