Triple
T19359929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iringa Region |
E484249
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Hehe |
—
|
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: Hehe | Statement: [Iringa Region, language, Hehe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hehe Context triple: [Iringa Region, language, Hehe]
-
A.
Hehe
chosen
Hehe is a Bantu language spoken primarily by the Hehe people of south-central Tanzania.
-
B.
Heh
Heh is an ancient Egyptian deity personifying infinite space and eternity, often depicted as a frog-headed god associated with the primordial chaos.
-
C.
EHEH
EHEH is the ICAO airport code for Eindhoven Airport, a major regional airport in the Netherlands.
-
D.
Hihi
Hihi is a small coastal settlement in New Zealand’s Northland region, known for its beaches and proximity to Doubtless Bay.
-
E.
H’m
H’m is a poetry collection by Welsh poet R. S. Thomas that reflects his characteristically austere, spiritually searching, and rural-themed verse.
- 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_69d8e8d305088190ad13571532aa454c |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e6190b343c81909734ba776fd196dc |
completed | April 20, 2026, 12:16 p.m. |
Created at: April 10, 2026, 1:34 p.m.