Triple
T6864593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ezaki Glico Co., Ltd. |
E158365
|
entity |
| Predicate | notableProduct |
P1448
|
FINISHED |
| Object | Pretz |
E623305
|
NE 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: Pretz | Statement: [Ezaki Glico Co., Ltd., notableProduct, Pretz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pretz Context triple: [Ezaki Glico Co., Ltd., notableProduct, Pretz]
-
A.
Pretz
chosen
Pretz is a popular Japanese snack brand of thin, savory biscuit sticks produced by Ezaki Glico.
-
B.
Twisted Tails Pretzels
Twisted Tails Pretzels is a snack stand in Busch Gardens Tampa’s Pantopia area known for serving freshly baked soft pretzels and related treats.
-
C.
Pepis
Pepis is an alternative historical spelling of the surname Pepys, most famously associated with the 17th-century English diarist Samuel Pepys.
-
D.
Utz
Utz is a 1992 British drama film, based on Bruce Chatwin’s novel, about an eccentric porcelain collector in Communist-era Prague.
-
E.
Brot-Dessous
Brot-Dessous is a small former municipality in the canton of Neuchâtel in western Switzerland, situated along the Areuse River in the Jura region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c68830cdbc8190a8301c7a9d9f651a |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d88af6d88190ac9faa32fa1bfa0e |
completed | March 27, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7428b2fe88190ac1798922e2b9620 |
completed | March 28, 2026, 2:52 a.m. |
Created at: March 27, 2026, 2:21 p.m.