Triple
T1040314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gheg |
E22454
|
entity |
| Predicate | isMutuallyIntelligibleWith |
P7448
|
FINISHED |
| Object | Tosk |
E22786
|
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: Tosk | Statement: [Gheg, isMutuallyIntelligibleWith, Tosk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tosk Context triple: [Gheg, isMutuallyIntelligibleWith, Tosk]
-
A.
Tosk
chosen
Tosk is the southern variety of Albanian that forms the basis of the standard Albanian language.
-
B.
Turoyo
Turoyo is a modern Neo-Aramaic language traditionally spoken by Syriac Orthodox Christian communities from the Tur Abdin region of southeastern Turkey and neighboring areas.
-
C.
Micali
Micali is an Italian surname most notably associated with Silvio Micali, a Turing Award–winning computer scientist and cryptographer.
-
D.
Ibzan
Ibzan is a minor biblical judge of Israel mentioned in the Book of Judges, known for his large family and brief period of leadership.
-
E.
Anjezë
Anjezë is the birth name of Mother Teresa, the Catholic nun and missionary renowned for her humanitarian work among the poor in Kolkata, India.
- 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_69a493d91478819094cc01fb65564bc1 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b82e4d2c81909ca1264852baf04d |
completed | March 1, 2026, 10:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac3bc58d8c8190b9dc7a4bc986abcb |
completed | March 7, 2026, 2:52 p.m. |
Created at: March 1, 2026, 7:41 p.m.