Triple
T21655010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anjediva Island |
E534437
|
entity |
| Predicate | hasHistoricalStructureType |
P66217
|
FINISHED |
| Object | fort |
—
|
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: fort | Statement: [Anjediva Island, hasHistoricalStructureType, fort]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHistoricalStructureType Context triple: [Anjediva Island, hasHistoricalStructureType, fort]
-
A.
hasStructureHistory
Indicates that there exists a record or account detailing the past states, changes, or development of a structure over time.
-
B.
hasHistoricalRegionType
Indicates that a historical region is associated with a specific type or classification of historical region.
-
C.
hasHistoricalEntity
Indicates a relationship where one entity includes, references, or is associated with another entity that existed or is defined in a past historical context.
-
D.
hasTypeHistory
Indicates that an entity is associated with a record or sequence of its past and present types or classifications over time.
-
E.
historicalType
chosen
Indicates that one entity classifies or characterizes another in terms of its role, status, or category within a historical context.
- 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_69e0c467e1f48190af2650b19175abc4 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef59176b28819092384fc5f8968022 |
completed | April 27, 2026, 12:39 p.m. |
| PD | Predicate disambiguation | batch_69e696826c3c81909270791e79760937 |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:36 p.m.