Triple
T22773299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madā’in |
E563615
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Asbānbar |
—
|
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: Asbānbar | Statement: [Madā’in, hasPart, Asbānbar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asbānbar Context triple: [Madā’in, hasPart, Asbānbar]
-
A.
Asbānbar
chosen
Asbānbar was a district or quarter within the ancient city complex of Al-Mada’in (Ctesiphon) in Mesopotamia, likely associated with the Sasanian imperial capital area.
-
B.
Abasár
Abasár is a village in northern Hungary known for its wine production and location near the Mátra Mountains.
-
C.
Barzanji
Barzanji is a Kurdish family name historically associated with influential religious and political leaders in the region of Iraqi Kurdistan.
-
D.
Barzan
Barzan is a given name notably borne by Barzan Ibrahim al-Tikriti, a prominent Iraqi intelligence chief and half-brother of Saddam Hussein.
-
E.
Bakhdida
Bakhdida is a historically Assyrian Christian town in northern Iraq, known for its ancient churches and location in the Nineveh Plains near Mosul.
- 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_69e24554497c819080b996e071de27c2 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17b6040048190a36fa759e06136ea |
completed | April 29, 2026, 3:30 a.m. |
Created at: April 17, 2026, 3:27 p.m.