Triple
T18747225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hadramawt |
E458434
|
entity |
| Predicate | majorCity |
P316
|
FINISHED |
| Object | Tarim |
—
|
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: Tarim | Statement: [Hadramawt, majorCity, Tarim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tarim Context triple: [Hadramawt, majorCity, Tarim]
-
A.
Tarim
chosen
Tarim is an ancient town in Yemen’s Hadhramaut region renowned as a historic center of Islamic scholarship and traditional architecture.
-
B.
Tarim Basin
The Tarim Basin is a large endorheic desert basin in northwest China’s Xinjiang region, historically a key crossroads of the Silk Road and home to diverse ancient cultures.
-
C.
Kharan
Kharan is a town in Balochistan, Pakistan, serving as the administrative center of Kharan District.
-
D.
Yarkand
Yarkand is an ancient oasis town and historical region in southwestern Xinjiang, China, that served as a key hub on the Silk Road.
-
E.
Zaitian
Zaitian was the personal name of the Guangxu Emperor, a late Qing dynasty ruler of China known for his attempted modernization reforms and his confinement under Empress Dowager Cixi.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e576936cf08190b3c0d2f4e8a616fc |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 10, 2026, 11:51 a.m.