Triple
T3676877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chick-fil-A |
E78013
|
entity |
| Predicate | menuFeature |
P19940
|
FINISHED |
| Object | pressure-cooked chicken |
—
|
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: pressure-cooked chicken | Statement: [Chick-fil-A, menuFeature, pressure-cooked chicken]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: menuFeature Context triple: [Chick-fil-A, menuFeature, pressure-cooked chicken]
-
A.
featuresAction
Indicates that one entity includes, presents, or showcases a particular action as a notable characteristic or component.
-
B.
featuresSetting
Indicates that something includes, presents, or highlights a particular setting as a notable or primary aspect.
-
C.
hasMenuItem
chosen
Indicates that one entity (typically a menu or menu section) includes or offers another entity as one of its menu items.
-
D.
hasKidsMenu
Indicates that an establishment offers a menu specifically designed for children.
-
E.
maintenanceFeature
Indicates that one entity serves as a maintenance-related feature, capability, or component associated with 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_69ad85e18c1c8190be8aafb227f39f48 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc4643cf08190b2d10ddf4aac7407 |
completed | March 8, 2026, 6:48 p.m. |
| PD | Predicate disambiguation | batch_69adb84be1fc81909721c871babb4633 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:25 p.m.