Triple
T25766830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teiwa language |
E648904
|
entity |
| Predicate | hasMajorReferenceGrammar |
P75570
|
FINISHED |
| Object | Teiwa (2010 grammar by Marian Klamer) |
—
|
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: Teiwa (2010 grammar by Marian Klamer) | Statement: [Teiwa language, hasMajorReferenceGrammar, Teiwa (2010 grammar by Marian Klamer)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMajorReferenceGrammar Context triple: [Teiwa language, hasMajorReferenceGrammar, Teiwa (2010 grammar by Marian Klamer)]
-
A.
hasReferenceGrammar
chosen
Indicates that an entity is associated with or described by a specific reference grammar resource.
-
B.
hasReferenceGrammarBy
Indicates that an entity is associated with or described by a reference grammar authored or compiled by a specified agent.
-
C.
hasGrammar
Indicates that an entity possesses, follows, or is associated with a particular system of grammatical rules or structure.
-
D.
hasMajorLexifier
Indicates that a language has another language as its primary lexical source or main contributor of its vocabulary.
-
E.
hasGrammarFrom
Indicates that one entity derives or uses its grammatical structure or rules from another entity.
- 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_69e7ab322db0819092d6a2b3d4572e01 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: April 22, 2026, 5:11 a.m.