Triple
T21892673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faryab Province |
E540592
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Andkhoy |
—
|
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: Andkhoy | Statement: [Faryab Province, hasCity, Andkhoy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andkhoy Context triple: [Faryab Province, hasCity, Andkhoy]
-
A.
Andkhoy
chosen
Andkhoy is a town in northern Afghanistan known historically as a regional trading center near the Turkmenistan border.
-
B.
Salyan
Salyan is a town in Azerbaijan known for its location in the Kura River lowlands and its role as a regional administrative and economic center.
-
C.
Dakghar
Dakghar is a renowned Bengali play by Rabindranath Tagore that poignantly explores themes of freedom, imagination, and the inner life of a sick child.
-
D.
Khoksa
Khoksa is a town and administrative unit in western Bangladesh, situated within the Kushtia District of the Khulna Division.
-
E.
Raqchi
Raqchi is a significant Inca archaeological complex in Peru, known for its monumental Temple of Wiracocha and extensive ceremonial and residential structures.
- 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_69e0c47a95908190ae3e19b716accb3d |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fc46dd481908a119cfbe26564a3 |
completed | April 28, 2026, 8:59 p.m. |
Created at: April 16, 2026, 7:06 p.m.