Triple
T29915966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cantonese stir-fried shrimp with eggs |
E759795
|
entity |
| Predicate | commonShrimpType |
P194362
|
FINISHED |
| Object | fresh shrimp |
—
|
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: fresh shrimp | Statement: [Cantonese stir-fried shrimp with eggs, commonShrimpType, fresh shrimp]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonShrimpType Context triple: [Cantonese stir-fried shrimp with eggs, commonShrimpType, fresh shrimp]
-
A.
typicalFishType
Indicates that one entity is the fish type that is most commonly or characteristically associated with the other entity.
-
B.
salmonType
Indicates that one entity is classified as a specific type or variety of salmon in relation to another entity.
-
C.
seafoodSpecialty
Indicates that one entity specializes in preparing, serving, or producing seafood as a primary focus or notable expertise.
-
D.
nativeFish
Indicates that the fish species is originally from, and naturally occurs in, the specified geographic area or ecosystem.
-
E.
coralType
Indicates the specific kind or classification of coral associated with an entity.
- 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_69f2246189fc8190996b63ee1f9a2374 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fd6dbd1b648190b1a0b391c03aebc5 |
completed | May 8, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_69fd6a9020548190bbfa845360ac85fb |
completed | May 8, 2026, 4:46 a.m. |
| PDg | Predicate description generation | batch_69fd6dbc3ac0819093fbcfe95f12b93d |
completed | May 8, 2026, 4:59 a.m. |
Created at: April 29, 2026, 6:12 p.m.