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.