Triple
T32788139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mardin Castle |
E838552
|
entity |
| Predicate | usedInHistory |
P2417
|
FINISHED |
| Object | regional 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: regional defense | Statement: [Mardin Castle, usedInHistory, regional defense]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInHistory Context triple: [Mardin Castle, usedInHistory, regional defense]
-
A.
historicallyUsedFor
chosen
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.
-
B.
usedInPastBy
Indicates that an entity was previously utilized or employed by another entity at some time in the past.
-
C.
usedAt
Indicates that something is employed, applied, or utilized at a particular place, time, or context.
-
D.
usedInPast
Indicates that an entity has been utilized or employed at some point in the past, prior to the current time or context.
-
E.
hasHistoryIn
Indicates that an entity has a past involvement, presence, or record of activity within a particular domain, context, or location.
- 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_69f3493b83f48190be335cd42465cecf |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fe0d165a48819098b854318a50d76c |
completed | May 8, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69fe0931002481908a95b34f95e9f64e |
completed | May 8, 2026, 4:02 p.m. |
Created at: May 1, 2026, 1:14 a.m.