Triple

T11707677
Position Surface form Disambiguated ID Type / Status
Subject Akan states E278289 entity
Predicate hadCapitalIn P70941 FINISHED
Object various regional centers 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: various regional centers | Statement: [Akan states, hadCapitalIn, various regional centers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hadCapitalIn
Context triple: [Akan states, hadCapitalIn, various regional centers]
  • A. hasCoCapital
    Indicates that two or more cities share the status and functions of being capital cities of the same political or administrative entity.
  • B. hasCapitalDuringProcess
    Indicates that an entity possesses or controls capital (financial or resource assets) throughout the duration of a specified process or activity.
  • C. hasCapital
    Indicates that a place or political entity has a specific city designated as its capital.
  • D. usedCapital chosen
    Indicates that an entity made use of a particular capital city as its seat of government or primary administrative center.
  • E. hasAssociatedCapital
    Indicates that an entity is linked to a specific capital city that serves as its primary administrative or political center.
  • 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_69d6aaff2ce88190b4a1e4b341ad5377 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a49de0388190a063739426bf90e8 completed April 10, 2026, 7:19 a.m.
PD Predicate disambiguation batch_69d88a7d483081909c2a101087515d74 completed April 10, 2026, 5:28 a.m.
Created at: April 8, 2026, 9:40 p.m.