Triple
T3569403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahmud Shah Durrani |
E75530
|
entity |
| Predicate | house |
P1505
|
FINISHED |
| Object | Sadozai |
E411980
|
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: Sadozai | Statement: [Mahmud Shah Durrani, house, Sadozai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sadozai Context triple: [Mahmud Shah Durrani, house, Sadozai]
-
A.
Sadozai
chosen
Sadozai is a Pashtun royal dynasty and clan historically associated with the founding rulers of the Durrani Empire in Afghanistan.
-
B.
Masaharu
Masaharu is a Japanese masculine given name that can be written with various kanji combinations and is borne by several notable figures in Japanese history and culture.
-
C.
Itagaki
Itagaki is a Japanese surname associated with several notable historical and contemporary figures in Japan.
-
D.
Takayoshi
Takayoshi is a Japanese given name notably borne by Kido Takayoshi, a key samurai and statesman of the Meiji Restoration.
-
E.
Takanami
Takanami was a Japanese destroyer of the Imperial Japanese Navy during World War II, notable for being sunk in the Battle of Tassafaronga in 1942.
- 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_69ad85d512708190829c8b2d3a2ccfb8 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0c1ecb081909051bcc1f38eea31 |
completed | March 8, 2026, 6:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a81fdf888190a4d9f75471b9ec39 |
completed | March 14, 2026, 6:25 p.m. |
Created at: March 8, 2026, 3:21 p.m.