Triple

T28923894
Position Surface form Disambiguated ID Type / Status
Subject Justice Lawrence Wargrave E733591 entity
Predicate plansLocation P44626 FINISHED
Object Soldier Island
Soldier Island is the isolated, fictional setting off the coast of Devon where the events of Agatha Christie’s mystery novel "And Then There Were None" take place.
 E1839236 NE FINISHED

How this triple was built (3 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: Soldier Island | Statement: [Justice Lawrence Wargrave, plansLocation, Soldier Island]
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: Soldier Island
Triple: [Justice Lawrence Wargrave, plansLocation, Soldier Island]
Generated description
Soldier Island is the isolated, fictional setting off the coast of Devon where the events of Agatha Christie’s mystery novel "And Then There Were None" take place.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: plansLocation
Context triple: [Justice Lawrence Wargrave, plansLocation, Soldier Island]
  • A. locationOfPlanning chosen
    Indicates the place or setting where the planning activity or process occurs.
  • B. plannedLocation
    Indicates the intended or scheduled location where an entity is expected to be or an event is planned to occur.
  • C. countryPlanningAgency
    Indicates that a given organization functions as a governmental or official body responsible for planning and development activities within a specific country.
  • D. decisionPlace
    Indicates the location where a decision is made or formally determined.
  • E. generalateLocation
    Indicates the location where a generalate (central administrative headquarters of a religious or similar organization) is situated.
  • F. None of above.

Provenance (6 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_69f05b0a5cc0819094828367ae204b70 completed April 28, 2026, 7 a.m.
NER Named-entity recognition batch_69f65b1d1c688190b035919575bb2164 completed May 2, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_6a24d41f1b3481908de0d8b3bb518564 completed June 7, 2026, 2:14 a.m.
NEDg Description generation batch_6a24d8b850a48190a9c2618c63fd5f50 completed June 7, 2026, 2:34 a.m.
NED2 Entity disambiguation (via description) batch_6a24dc7507e881908586b8a971c9be80 completed June 7, 2026, 2:50 a.m.
PD Predicate disambiguation batch_69f659d02f1c8190831758ac52bb54e4 completed May 2, 2026, 8:08 p.m.
Created at: April 28, 2026, 8:22 a.m.