Triple
T8674720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawrami |
E205884
|
entity |
| Predicate | hasMorphologicalFeatures |
P7162
|
FINISHED |
| Object | ergative alignment in past tenses |
—
|
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: ergative alignment in past tenses | Statement: [Hawrami, hasMorphologicalFeatures, ergative alignment in past tenses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMorphologicalFeatures Context triple: [Hawrami, hasMorphologicalFeatures, ergative alignment in past tenses]
-
A.
hasVerbalMorphology
Indicates that one linguistic element exhibits verbal inflectional properties or patterns in relation to another.
-
B.
hasLinguisticFeature
chosen
Indicates that an entity possesses a particular linguistic property, trait, or characteristic.
-
C.
hasVerbalFeature
Indicates that an entity possesses a specific verbal property, characteristic, or behavior related to speech or language.
-
D.
hasNominalMorphology
Indicates that an entity possesses a system of nominal morphology, such as inflectional or derivational markers on nouns.
-
E.
relatedMorphologicalFeature
Indicates that one entity is connected to another through a shared or corresponding morphological feature or 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_69ca83529a9c8190b5c075b4f14636ed |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4ae6d19c8190be003f7901c0468d |
completed | March 31, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69cc4567b5c881908d9ec5dcfc783fac |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:31 p.m.