Triple
T29265599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bananas Foster |
E741968
|
entity |
| Predicate | isOftenServedOnOccasion |
P14787
|
FINISHED |
| Object | special occasions |
—
|
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: special occasions | Statement: [Bananas Foster, isOftenServedOnOccasion, special occasions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOftenServedOnOccasion Context triple: [Bananas Foster, isOftenServedOnOccasion, special occasions]
-
A.
servingOccasion
chosen
Indicates the occasion, event, or context during which something (typically food or drink) is served.
-
B.
usedOnOccasions
Indicates that something is employed or utilized during specific events, times, or circumstances rather than continuously.
-
C.
frequentOccasion
Indicates that a particular event, situation, or condition occurs repeatedly or commonly over time.
-
D.
eatenOnOccasion
Indicates that one entity is consumed or eaten by another only at certain times or under specific circumstances, rather than regularly or habitually.
-
E.
onOccasionOf
Indicates that one event, action, or state occurs in connection with, or is triggered by, a particular occasion or special event.
- 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_69f0912065c08190bddd23e20e8ef18e |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 12:44 p.m.