Triple
T22524352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tananarive |
E556860
|
entity |
| Predicate | isHistoricNameOf |
P66486
|
FINISHED |
| Object | capital of Madagascar |
—
|
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: capital of Madagascar | Statement: [Tananarive, isHistoricNameOf, capital of Madagascar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isHistoricNameOf Context triple: [Tananarive, isHistoricNameOf, capital of Madagascar]
-
A.
historicalNameType
Indicates that the relationship specifies the type or category of a historical name associated with an entity.
-
B.
historicalNameGivenBy
Indicates that one entity is the name historically assigned to another entity by a specific source, culture, or period.
-
C.
hasHistoricNameVariant
chosen
Indicates that an entity has an alternative name that was used in a historical period or past context.
-
D.
historicalNameUsedIn
Indicates that a historical or former name was used to refer to a particular entity in some context.
-
E.
hasHistoricNickname
Indicates that an entity is known by a nickname that has historical significance or longstanding traditional use.
- 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_69e11e5657e881909f16ca58352c50da |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15e34590c81909e4ed1c95f13a199 |
completed | April 29, 2026, 1:26 a.m. |
| PD | Predicate disambiguation | batch_69ee625e3b408190a60c759fb0b28fe2 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 16, 2026, 8:51 p.m.