Triple
T29465975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | as-Safa region |
E747380
|
entity |
| Predicate | inscriptionScriptFamily |
P22774
|
FINISHED |
| Object | Ancient North Arabian scripts |
—
|
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: Ancient North Arabian scripts | Statement: [as-Safa region, inscriptionScriptFamily, Ancient North Arabian scripts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionScriptFamily Context triple: [as-Safa region, inscriptionScriptFamily, Ancient North Arabian scripts]
-
A.
inscriptionLayout
Indicates how an inscription is spatially arranged or formatted in relation to the surface or object it appears on.
-
B.
inscriptionFeature
Indicates that one entity bears or contains an inscribed element or marking that is treated as a notable feature in relation to another entity.
-
C.
styleFamily
Indicates that one style is grouped within the same stylistic family or category as another style.
-
D.
inscriptionType
Indicates the specific kind or category of inscription associated with an entity (e.g., dedicatory, funerary, commemorative).
-
E.
scriptOfInscription
chosen
Indicates the writing system or script in which a given inscription is written.
- 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_69f0bd4125f88190b56104591351619c |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66ba7afcc8190a98cfe4f88ab7bc7 |
completed | May 2, 2026, 9:24 p.m. |
| PD | Predicate disambiguation | batch_69f66339175c819080bd70f0ff7057b1 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 3:53 p.m.