Triple
T11578461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dogon languages |
E274563
|
entity |
| Predicate | haveBasicWordOrder |
P1249
|
FINISHED |
| Object | SOV |
—
|
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: SOV | Statement: [Dogon languages, haveBasicWordOrder, SOV]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveBasicWordOrder Context triple: [Dogon languages, haveBasicWordOrder, SOV]
-
A.
hasBasicWordOrder
chosen
Indicates the typical sequence in which core sentence elements (such as subject, verb, and object) are ordered in a language.
-
B.
hasV2WordOrder
Indicates that a clause or language follows verb-second (V2) word order, where the finite verb consistently appears in the second position of the sentence.
-
C.
hasVerseOrder
Indicates that one verse is ordered or sequenced in relation to another verse within a structured text.
-
D.
hasBasicLetters
Indicates that an entity contains or is composed of fundamental alphabetic characters, without additional symbols or diacritics.
-
E.
hasClauseStructure
Indicates that one linguistic unit exhibits a particular internal clause configuration or pattern in relation to another specified clause structure.
- 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_69d6aae5ac3c81908d2b0a3a665665b2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8904b46288190890ecafd6ceb0c3d |
completed | April 10, 2026, 5:53 a.m. |
| PD | Predicate disambiguation | batch_69d85dcbacd0819094d4a1237055affa |
completed | April 10, 2026, 2:17 a.m. |
Created at: April 8, 2026, 9:38 p.m.