Triple
T16819748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rudaki |
E408853
|
entity |
| Predicate | deathPlace |
P21
|
FINISHED |
| Object | Rudak |
E1235255
|
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: Rudak | Statement: [Rudaki, deathPlace, Rudak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rudak Context triple: [Rudaki, deathPlace, Rudak]
-
A.
Rudak
chosen
Rudak is a village in Tajikistan known primarily as the birthplace of the Persian poet Rudaki.
-
B.
Rudsar
Rudsar is a coastal city in northern Iran known for its lush landscapes, rice paddies, and proximity to the Caspian Sea.
-
C.
Rudabeh
Rudabeh is a legendary Persian princess and queen in the Shahnameh, renowned for her beauty, wisdom, and as the mother of the hero Rostam.
-
D.
Jajrud
Jajrud is a river in northern Iran that flows through the Alborz Mountains toward the Tehran region.
-
E.
Tuyserkan
Tuyserkan is a city in western Iran known for its walnut orchards, traditional handicrafts, and historical sites such as ancient tombs and bazaars.
- 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_69d88394566c8190b3dcbdc72935f7fa |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b2e56b9c8190a35ad9c463954fbf |
completed | April 18, 2026, 4:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00bb11f8708190ae762a28710e4246 |
completed | May 10, 2026, 5:06 p.m. |
Created at: April 10, 2026, 5:23 a.m.