Triple
T14554550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iraq-i Ajam |
E341504
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object | Qumis |
E1077995
|
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: Qumis | Statement: [Iraq-i Ajam, hasMajorCity, Qumis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qumis Context triple: [Iraq-i Ajam, hasMajorCity, Qumis]
-
A.
Qumis
chosen
Qumis was an ancient historical region in north-central Iran, situated along key trade routes and adjacent to Tabaristan.
-
B.
Kvasiny
Kvasiny is a village in the Hradec Králové Region of the Czech Republic best known for hosting a major Škoda Auto manufacturing plant.
-
C.
Habaswein
Habaswein is a small town in Kenya known for its predominantly pastoralist community and its location within the arid, sparsely populated northeastern region of the country.
-
D.
Usakhelauri wine
Usakhelauri wine is a rare, naturally semi-sweet Georgian red wine prized for its aromatic complexity and limited production from the Usakhelauri grape.
-
E.
Khvanchkara wine
Khvanchkara wine is a semi-sweet red Georgian wine, traditionally made from Aleksandrouli and Mujuretuli grapes, renowned for its rich berry flavors and natural sweetness.
- 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_69d822db9c8481908213ceb39585f792 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb2f00cec8190a7b6482d18b9a216 |
completed | April 14, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd8ab9a5ac81908779a3c8701353fa |
completed | May 8, 2026, 7:03 a.m. |
Created at: April 10, 2026, 1:23 a.m.