Triple
T14933985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ishkashimi |
E372341
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Munji |
E230686
|
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: Munji | Statement: [Ishkashimi, closelyRelatedTo, Munji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Munji Context triple: [Ishkashimi, closelyRelatedTo, Munji]
-
A.
Munji
chosen
Munji is a lesser-known Eastern Iranian language spoken by the Munji people in the remote Munjan Valley of northeastern Afghanistan.
-
B.
Mahwa
Mahwa is a town located in the Dausa district of the Indian state of Rajasthan.
-
C.
Muye
Muye was the site of an ancient Chinese battlefield where the Zhou forces decisively overthrew the Shang dynasty.
-
D.
Mang’anja
Mang’anja is a Bantu language variety spoken primarily in southern Malawi, closely related to other Sena–Nyanja languages.
-
E.
Minyong
Minyong is a subgroup of the Adi people, an indigenous community of Arunachal Pradesh in Northeast India known for its distinct language and cultural traditions.
- 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_69d85cc9da0c81908d583ca3f63a3908 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded646a0808190ba5c0c91bde011c5 |
completed | April 15, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe7e8c8d188190b027f14256b0ce01 |
completed | May 9, 2026, 12:23 a.m. |
Created at: April 10, 2026, 2:37 a.m.