Triple
T6864633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glico |
E158366
|
entity |
| Predicate | notableProduct |
P1448
|
FINISHED |
| Object | Giant Cone |
E623310
|
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: Giant Cone | Statement: [Glico, notableProduct, Giant Cone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Giant Cone Context triple: [Glico, notableProduct, Giant Cone]
-
A.
Giant Cone
chosen
Giant Cone is a popular Japanese ice cream brand known for its large, cone-shaped treats produced by Ezaki Glico.
-
B.
Passu Cones
Passu Cones are a striking group of sharply pointed mountain peaks in Pakistan’s Hunza Valley, renowned for their dramatic, jagged skyline within the Karakoram range.
-
C.
Opal Cone
Opal Cone is a volcanic feature in British Columbia, Canada, known as a well-preserved cinder cone on the southeastern flank of Mount Garibaldi.
-
D.
Treble Cone
Treble Cone is a major South Island New Zealand ski area near Wānaka, known for its long runs, challenging terrain, and expansive views over Lake Wānaka.
-
E.
Inferno Cone
Inferno Cone is a prominent cinder cone viewpoint within Idaho’s Craters of the Moon lava field, offering panoramic views of the surrounding volcanic landscape.
- 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.