Triple
T34756076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Candoshi language |
E1001925
|
entity |
| Predicate | languageStatusInPeru |
P176357
|
FINISHED |
| Object | recognized indigenous language |
—
|
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: recognized indigenous language | Statement: [Candoshi language, languageStatusInPeru, recognized indigenous language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageStatusInPeru Context triple: [Candoshi language, languageStatusInPeru, recognized indigenous language]
-
A.
languageStatusOfLatin
Indicates the status or condition of the Latin language in a given context or entity.
-
B.
idiomasOficiales
Indicates that one or more languages are officially recognized or designated for use by a given entity (such as a country, region, or institution).
-
C.
ethnicLanguageStatus
Indicates the status or role of a language in relation to a particular ethnic group (e.g., primary, secondary, heritage, or minority language).
-
D.
languageStatusSource
Indicates the source or authority from which the information about a language’s status is derived.
-
E.
localLanguageStatus
chosen
Indicates the status or condition of a language as used within a specific local or regional context.
- 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_69f76db0fb30819096709d43f9a1f45f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a0082989e6c819099fea0e706332e37 |
completed | May 10, 2026, 1:05 p.m. |
| PD | Predicate disambiguation | batch_6a0081ed6a1481908baf472876e28db9 |
completed | May 10, 2026, 1:02 p.m. |
Created at: May 3, 2026, 3:59 p.m.