Triple
T37199436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kindah kingdom |
E921686
|
entity |
| Predicate | partiallyAttestedIn |
P192611
|
FINISHED |
| Object | South Arabian inscriptions |
—
|
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: South Arabian inscriptions | Statement: [Kindah kingdom, partiallyAttestedIn, South Arabian inscriptions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partiallyAttestedIn Context triple: [Kindah kingdom, partiallyAttestedIn, South Arabian inscriptions]
-
A.
alsoAttestedIn
Indicates that the same item, fact, or phenomenon is recorded or evidenced in another source, context, or location as well.
-
B.
partiallyProvenFor
Indicates that something has been shown to hold or be true for part of a domain or set of cases, but not yet for all cases.
-
C.
attestedBy
Indicates that the existence, occurrence, or validity of something is supported, confirmed, or documented by a specified source or authority.
-
D.
attestedAs
Indicates that something is documented, recorded, or certified as having a particular status, form, or property.
-
E.
partiallyHeldAt
Indicates that an entity is held or grasped in an incomplete, unstable, or not fully secure manner at a particular time or location.
- F. None of above. chosen
Provenance (4 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_69f76ea313a08190a54404cd1e47da90 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd19f791f48190bbb6f6047f9ddc59 |
completed | May 7, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69fd0df365948190bc9bfc7ffd46acd8 |
completed | May 7, 2026, 10:10 p.m. |
| PDg | Predicate description generation | batch_69fd19f6a7888190aa7eee2b87687c53 |
completed | May 7, 2026, 11:02 p.m. |
Created at: May 3, 2026, 4:15 p.m.