Triple
T22933902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Balantak language |
E569520
|
entity |
| Predicate | typologicalOrder |
P5753
|
FINISHED |
| Object | SVO (subject–verb–object) |
—
|
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: SVO (subject–verb–object) | Statement: [Balantak language, typologicalOrder, SVO (subject–verb–object)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typologicalOrder Context triple: [Balantak language, typologicalOrder, SVO (subject–verb–object)]
-
A.
typologicalGroup
Indicates that entities are classified together based on shared structural or typological characteristics.
-
B.
typology
chosen
Indicates a classification relationship in which entities are grouped or organized according to shared types, patterns, or structural characteristics.
-
C.
representationOrder
Indicates the sequence or hierarchy in which representations of entities are arranged or prioritized relative to one another.
-
D.
socialOrder
Indicates the hierarchical or structured arrangement of roles, statuses, and power relations that organize interactions within a society or group.
-
E.
orderOf
Indicates that one entity is arranged, ranked, or sequenced before or after another according to a specified ordering criterion.
- 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_69e24590862c8190858f180ad302adab |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18134484c8190b7311606c17d058d |
completed | April 29, 2026, 3:55 a.m. |
| PD | Predicate disambiguation | batch_69ef3b882e708190b0eb0c87021c75b8 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:44 p.m.