Triple
T23396468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kitsai language |
E559371
|
entity |
| Predicate | endonymUsedBySpeakers |
P1435
|
FINISHED |
| Object | Kichai (various spellings) |
—
|
LITERAL 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: Kichai (various spellings) | Statement: [Kitsai language, endonymUsedBySpeakers, Kichai (various spellings)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endonymUsedBySpeakers Context triple: [Kitsai language, endonymUsedBySpeakers, Kichai (various spellings)]
-
A.
hasEndonym
chosen
Indicates that an entity has a name or designation used by native speakers or within its own local language or community.
-
B.
isEndonym
Indicates that a name is used by a group to refer to themselves or their own place/language, rather than being an external or foreign designation.
-
C.
hasEndonymLanguage
Indicates that the language specified is the one in which a name or term is expressed in its own native or local form.
-
D.
ethnonymInLanguage
Indicates that a given term is the name used in a specified language to refer to the people of a particular ethnic group or nationality.
-
E.
isSpokenAs
Indicates that one entity is used as the spoken or verbal form of another entity (e.g., a word, name, or phrase).
- F. None of above.
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_69e24549610c8190a069d6411ce5f661 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a4dc48008190bdcf92f8d9a5232d |
completed | April 29, 2026, 6:27 a.m. |
| PD | Predicate disambiguation | batch_69f061dde2e481908308952f9c0d3c2e |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:36 p.m.