Triple
T21952605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Istriano |
E542103
|
entity |
| Predicate | refersToVarietySpokenIn |
P133827
|
FINISHED |
| Object | Šišan |
—
|
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: Šišan | Statement: [Istriano, refersToVarietySpokenIn, Šišan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Šišan Context triple: [Istriano, refersToVarietySpokenIn, Šišan]
-
A.
Šišan
chosen
Šišan is a village in Istria, Croatia, known as one of the traditional centers of the Istriot language and its cultural heritage.
-
B.
Shahdag
Shahdag is a prominent mountain in northeastern Azerbaijan, known for its high elevation and the nearby Shahdag Mountain Resort that makes it a major regional destination for skiing and outdoor recreation.
-
C.
Shahgarh
Shahgarh is a town in the Sagar district of the central Indian state of Madhya Pradesh.
-
D.
Kushk
Kushk is a town in northwestern Afghanistan near the Turkmenistan border, known as a local trade and transit center in Herat Province.
-
E.
Tashkurgan Sarikoli
Tashkurgan Sarikoli is an Eastern Iranian language spoken primarily by the Sarikoli people in the Tashkurgan region of Xinjiang, China.
- 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1243d43d8819084e280b129631288 |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:59 p.m.