Triple
T8857368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hidar |
E210790
|
entity |
| Predicate | alsoTransliteratedAs |
P5923
|
FINISHED |
| Object | Hidar ህዳር |
E210790
|
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: Hidar ህዳር | Statement: [Hidar, alsoTransliteratedAs, Hidar ህዳር]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hidar ህዳር Context triple: [Hidar, alsoTransliteratedAs, Hidar ህዳር]
-
A.
Hidar
chosen
Hidar is the third month of the Ethiopian calendar, roughly corresponding to November in the Gregorian calendar.
-
B.
Habr Gedir
Habr Gedir is a major subclan of the Hawiye clan-family in Somalia, historically influential in the country’s politics, conflicts, and business networks.
-
C.
Gidar
Gidar is an Afroasiatic Chadic language spoken primarily in parts of northern Cameroon and neighboring regions.
-
D.
Idhna
Idhna is a Palestinian town located in the southern West Bank, west of Hebron, known for its agricultural lands and proximity to the Green Line.
-
E.
Yidgha
Yidgha is an Eastern Iranian language spoken primarily in parts of northern Pakistan, closely related to the Munji language and noted for its conservative phonological features.
- 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_69ca838bbddc8190ab546d737e5d350f |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60e3b62c8190bf779e7e1db767f6 |
completed | April 1, 2026, 12:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa0a8c0a48190b362685682e13460 |
completed | April 3, 2026, 11:12 a.m. |
Created at: March 30, 2026, 6:50 p.m.