Triple
T23925063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amasya Castle |
E602326
|
entity |
| Predicate | primaryUseInAntiquity |
P93071
|
FINISHED |
| Object | military defense |
—
|
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: military defense | Statement: [Amasya Castle, primaryUseInAntiquity, military defense]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryUseInAntiquity Context triple: [Amasya Castle, primaryUseInAntiquity, military defense]
-
A.
primaryFunctionInAntiquity
chosen
Indicates the main role or purpose an entity served during ancient times.
-
B.
discoveredInAntiquity
Indicates that something was found, identified, or recognized during ancient historical times rather than in the modern era.
-
C.
storedInAntiquityAs
Indicates that something was kept, preserved, or archived during ancient times in a particular place or container.
-
D.
historicallyUsedFor
Indicates that something served a particular function or purpose at some point in the past, even if it may no longer be used that way now.
-
E.
originalPrimaryUse
Indicates that something was first or chiefly intended to be used for a particular purpose or function.
- 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_69e2953b928c819095395fa87baca583 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cf1bdf108190b3c04146af8c3b3c |
completed | April 29, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:42 p.m.