Triple
T37570982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yoruba monarchy |
E934686
|
entity |
| Predicate | hasCapitalInstitution |
P64535
|
FINISHED |
| Object | palace court |
—
|
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: palace court | Statement: [Yoruba monarchy, hasCapitalInstitution, palace court]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCapitalInstitution Context triple: [Yoruba monarchy, hasCapitalInstitution, palace court]
-
A.
hasStateInstitution
Indicates that a particular state possesses, governs, or is served by a specific institution operating under its authority or within its jurisdiction.
-
B.
hasFinancialInstitution
Indicates that one entity is associated with or linked to a financial institution, such as a bank or similar financial service provider.
-
C.
isMajorInstitutionIn
Indicates that an institution is a primary or highly significant organization located within or associated with a particular place or region.
-
D.
hasInstitutions
chosen
Indicates that one entity possesses, contains, or is associated with one or more institutions.
-
E.
hasSecurityInstitution
Indicates that an entity is associated with, governed by, or protected through a particular security-related institution or organization.
- 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_69f76ecd99148190be327e391a70f5b6 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a001cc0ff588190bb7c8a6fd427d02b |
completed | May 10, 2026, 5:50 a.m. |
| PD | Predicate disambiguation | batch_6a001b3ea18c8190aeda7a32b2697490 |
completed | May 10, 2026, 5:44 a.m. |
Created at: May 3, 2026, 4:17 p.m.