Triple
T7492955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ha language |
E177051
|
entity |
| Predicate | alternateName |
P39
|
FINISHED |
| Object | Kiha |
E177052
|
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: Kiha | Statement: [Ha language, alternateName, Kiha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kiha Context triple: [Ha language, alternateName, Kiha]
-
A.
Kiha
chosen
Kiha is a Bantu language spoken by the Ha people of the Kigoma region in western Tanzania.
-
B.
Hankyu 1300 series
The Hankyu 1300 series is a Japanese electric multiple unit train type operated by Hankyu Railway, primarily used for commuter services in the Osaka area.
-
C.
Hankyu 5300 series
The Hankyu 5300 series is a Japanese electric multiple unit train type operated by Hankyu Railway, primarily used for commuter services in the Kansai region.
-
D.
Rokkō Liner
Rokkō Liner is an automated guideway transit line in Kobe, Japan, connecting the artificial island of Rokkō Island with the mainland.
-
E.
Hankyu 3300 series
The Hankyu 3300 series is a Japanese electric multiple unit train type operated by Hankyu Railway, primarily used for commuter services in the Osaka area.
- 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_69c69f2583808190bd1a4936c42a5815 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5784c908190b701959daf082625 |
completed | March 27, 2026, 9:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c83c7c60b8819090f2c4b16332c557 |
completed | March 28, 2026, 8:39 p.m. |
Created at: March 27, 2026, 3:43 p.m.