Triple
T19216296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Semiramis |
E480494
|
entity |
| Predicate | culture |
P1114
|
FINISHED |
| Object | Assyrian |
—
|
NE NERFINISHED |
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: Assyrian | Statement: [Semiramis, culture, Assyrian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Assyrian Context triple: [Semiramis, culture, Assyrian]
-
A.
Assyrian
Assyrian is a modern Eastern Aramaic language historically spoken by the Assyrian people of northern Mesopotamia and surrounding regions.
-
B.
Neo-Assyrian
Neo-Assyrian is a later dialect of the Akkadian language used in the Neo-Assyrian Empire for administration, literature, and inscriptions.
-
C.
Assyrians
Assyrians are an indigenous ethnic group of the Middle East, primarily Christian and descended from the ancient Mesopotamian civilization of Assyria.
-
D.
Old Assyrian
Old Assyrian is an early dialect of the Akkadian language used in the ancient city-state of Assur and in Old Assyrian trade colonies during the early second millennium BCE.
-
E.
Assyria
chosen
Assyria was an ancient Mesopotamian kingdom and later empire known for its powerful military, advanced administration, and influential cities such as Nineveh and Ashur.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa3a417c819083e2e276d44d4d89 |
completed | April 20, 2026, 10:04 a.m. |
Created at: April 10, 2026, 1:22 p.m.