Triple
T2220854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Darius I of Persia |
E48135
|
entity |
| Predicate | languageUsed |
P238
|
FINISHED |
| Object | Elamite |
E83627
|
NE 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: Elamite | Statement: [Darius I of Persia, languageUsed, Elamite]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elamite Context triple: [Darius I of Persia, languageUsed, Elamite]
-
A.
Elamite
chosen
Elamite is an ancient language of southwestern Iran, historically used in the kingdom of Elam and later as an administrative language under the Achaemenid Empire.
-
B.
Old Persian
Old Persian is an ancient Iranian language used in the Achaemenid Empire, primarily known from royal inscriptions such as those of Darius the Great.
-
C.
Akkadian
Akkadian is an extinct Semitic language of ancient Mesopotamia, historically used in Assyria and Babylonia and written in cuneiform script.
-
D.
Akkad
Akkad was an ancient Mesopotamian city and region best known as the center of the Akkadian Empire, one of the world’s earliest great empires.
-
E.
Avestan language
The Avestan language is an ancient Eastern Iranian language known primarily as the liturgical language of Zoroastrianism and the sacred texts of the Avesta.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88aa1ee708190862c8c378c41e9eb |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc0156c8c819083e3e3b6ede1e951 |
completed | March 7, 2026, 6:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae655df21c8190aa9624f15955c565 |
completed | March 9, 2026, 6:14 a.m. |
Created at: March 4, 2026, 7:46 p.m.