Triple
T32636443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khirbet Ataruz inscriptions |
E834355
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | West Semitic inscriptions |
C7425
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: West Semitic inscriptions Context triple: [Khirbet Ataruz inscriptions, instanceOf, West Semitic inscriptions]
-
A.
Proto-Canaanite inscription
A Proto-Canaanite inscription is an early alphabetic text, typically carved on stone or pottery in the Levant during the late second millennium BCE, representing one of the earliest known stages of the Canaanite (and thus later Phoenician and Hebrew) writing system.
-
B.
Semitic script
chosen
A Semitic script is a writing system historically used for Semitic languages, typically characterized by consonant-based alphabets (abjads) written from right to left.
-
C.
Ugaritic text
An Ugaritic text is an ancient written document from the city of Ugarit, inscribed in the Ugaritic cuneiform script and typically recording literary, religious, administrative, or legal content in the Ugaritic language.
-
D.
Hebrew inscription
A Hebrew inscription is a text carved, written, or engraved in the Hebrew language and script on a durable surface such as stone, metal, pottery, or parchment, often serving religious, commemorative, legal, or decorative purposes.
-
E.
ancient inscriptions
Ancient inscriptions are texts or symbols carved, engraved, or written on durable materials such as stone, metal, or clay by past civilizations, serving as primary evidence of their language, culture, beliefs, and historical events.
- F. None of above.
Provenance (1 batch)
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_69f3492dc2308190a88c6e30a3f3f576 |
completed | April 30, 2026, 12:21 p.m. |
Created at: May 1, 2026, 1:07 a.m.