Triple
T15996156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ad-Deir |
E387970
|
entity |
| Predicate | likelyOriginalFunction |
P14773
|
FINISHED |
| Object | Nabataean temple |
—
|
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: Nabataean temple | Statement: [Ad-Deir, likelyOriginalFunction, Nabataean temple]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: likelyOriginalFunction Context triple: [Ad-Deir, likelyOriginalFunction, Nabataean temple]
-
A.
originalFunction
Indicates that one entity serves as the initial or primary function from which another function or behavior is derived or defined.
-
B.
formerFunction
Indicates that an entity previously held a specific role, position, or function but no longer does so.
-
C.
possibleFunction
chosen
Indicates that an entity may serve, or is capable of serving, a particular function or role, without asserting that it actually does so.
-
D.
hasOriginalLocation
Indicates that an entity was initially located or situated at a specified place or position before any change or movement occurred.
-
E.
hasOriginalVersion
Indicates that one entity is the original or initial version from which another entity is derived or adapted.
- 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_69d86daa562c81908aacc179c0fe8fb5 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4e871c819082d7b1c1eaf5b4fe |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142d9d8e881909b559a3e3ca21d24 |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:55 a.m.