Triple
T15136681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Persian Iraq |
E361572
|
entity |
| Predicate | includesCity |
P3207
|
FINISHED |
| Object | Saveh |
E1167774
|
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: Saveh | Statement: [Persian Iraq, includesCity, Saveh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saveh Context triple: [Persian Iraq, includesCity, Saveh]
-
A.
Saveh
chosen
Saveh is a historic city in central Iran known as a regional commercial and agricultural center with ancient roots and traditional bazaars.
-
B.
Nurabad
Nurabad is a city in western Iran that serves as a local urban center within Lorestan Province.
-
C.
Hamadan
Hamadan is an ancient city in western Iran, historically significant as a major center of Persian Jewish life and one of the oldest continuously inhabited cities in the region.
-
D.
Sadabad
Sadabad is a town located in India’s culturally significant Braj region, traditionally associated with the life of Lord Krishna.
-
E.
Istakhr
Istakhr was an ancient city in southwestern Iran that served as an early political and religious center for the Sasanian dynasty near the ruins of Persepolis.
- 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_69d85a06450081909c5a14ea9851a15e |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e005b3f6f48190b1ed7c7b28feb7a6 |
completed | April 15, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a008a1d8e088190a2168952ab5dc687 |
completed | May 10, 2026, 1:37 p.m. |
Created at: April 10, 2026, 3:07 a.m.