Triple
T20504195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tampa Cuban sandwich |
E503383
|
entity |
| Predicate | typicalPicklePlacement |
P140337
|
FINISHED |
| Object | sliced pickles layered with meats |
—
|
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: sliced pickles layered with meats | Statement: [Tampa Cuban sandwich, typicalPicklePlacement, sliced pickles layered with meats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalPicklePlacement Context triple: [Tampa Cuban sandwich, typicalPicklePlacement, sliced pickles layered with meats]
-
A.
typicalPickleType
Indicates that something is the usual or standard type of pickle associated with a given context or entity.
-
B.
typicalStorePlacement
Indicates the usual or standard physical location where an item is placed or displayed within a store.
-
C.
plateLocation
Indicates the spatial position or placement of a plate relative to a reference location or object.
-
D.
nestLocation
Indicates the place or environment where an animal or organism builds or maintains its nest.
-
E.
hidingPlace
Indicates a location or object that serves as a concealed or secret place where something or someone is hidden.
- F. None of above. chosen
Provenance (4 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_69e0b4b1e52c8190894281cf7e3283ab |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69dc539908190a18918fd9b7a829d |
completed | April 20, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69e59fcdf6e08190a604204615dc56e6 |
completed | April 20, 2026, 3:38 a.m. |
| PDg | Predicate description generation | batch_69e5a6a824748190bbe6192d73f3c613 |
completed | April 20, 2026, 4:08 a.m. |
Created at: April 16, 2026, 11:35 a.m.