Triple
T22852947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boknal |
E566399
|
entity |
| Predicate | typicalFood |
P1016
|
FINISHED |
| Object | samgyetang |
—
|
NE NERFINISHED |
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: samgyetang | Statement: [Boknal, typicalFood, samgyetang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: samgyetang Context triple: [Boknal, typicalFood, samgyetang]
-
A.
samgyetang
chosen
Samgyetang is a traditional Korean soup made with a whole young chicken stuffed with glutinous rice and simmered in a ginseng-rich broth, often eaten for stamina during the hot summer months.
-
B.
Bulgogi
Bulgogi is a popular Korean dish of thinly sliced, marinated beef grilled or pan-cooked for a savory-sweet flavor.
-
C.
sundubu jjigae
Sundubu jjigae is a popular Korean stew made with uncurdled soft tofu, vegetables, and often seafood or meat, simmered in a spicy, flavorful broth.
-
D.
Ankwei-Goemai
Ankwei-Goemai is an alternative name for the Goemai language spoken by the Goemai people of central Nigeria.
-
E.
Mandu
Mandu is a historic fortified city in central India renowned for its Afghan-era architecture, romantic legends, and scenic hilltop setting.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2458750b481908a8e4cf4609cc6cf |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17eba65a881908c484262c3ee5212 |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:36 p.m.