Triple
T7024760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tana 'Ai language |
E162914
|
entity |
| Predicate | likelySubgroup |
P53577
|
FINISHED |
| Object | Flores languages |
—
|
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: Flores languages | Statement: [Tana 'Ai language, likelySubgroup, Flores languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: likelySubgroup Context triple: [Tana 'Ai language, likelySubgroup, Flores languages]
-
A.
notableSubgroup
Indicates that one group forms a particularly significant or noteworthy subset within a larger group.
-
B.
subgroupCategory
chosen
Indicates that one category functions as a more specific subgroup within the scope of another, broader category.
-
C.
likelyComposition
Indicates that one entity is probably a component or constituent part of another entity, though this compositional relationship is uncertain or inferred rather than definite.
-
D.
areSometimesGroupedWith
Indicates that two or more entities are occasionally but not consistently classified, treated, or considered together as part of the same group.
-
E.
coveredGroup
Indicates that one group or set is included within, or has its members protected or accounted for by, another group or arrangement.
- 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_69c6885b26248190a857541e3d10e299 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e5ecd4488190bf19e42de55da98b |
completed | March 27, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69c6e1b8118481909d76eb6616160e80 |
completed | March 27, 2026, 7:59 p.m. |
Created at: March 27, 2026, 2:35 p.m.