Triple
T28471833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cozy Cone Motel Cone 3 Chili Cone Queso |
E720458
|
entity |
| Predicate | coneNumber |
P164754
|
FINISHED |
| Object | 3 |
—
|
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: 3 | Statement: [Cozy Cone Motel Cone 3 Chili Cone Queso, coneNumber, 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coneNumber Context triple: [Cozy Cone Motel Cone 3 Chili Cone Queso, coneNumber, 3]
-
A.
ringNumber
Indicates that an entity is assigned a specific ring identifier or position number within a ring-structured system or sequence.
-
B.
coneType
Indicates the specific category or style of cone associated with an entity (e.g., type, shape, or design of the cone).
-
C.
coneColor
Indicates that one entity is the color attribute assigned to a cone-shaped object.
-
D.
hasCones
Indicates that an entity possesses or is characterized by cones (e.g., cone-shaped structures or cone-bearing features).
-
E.
pillarNumber
Indicates the specific numerical identifier assigned to a particular pillar within a set or structure.
- 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_69f01a5983f48190b7c1b8857245a4f7 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f64ee2913c8190b0c8ff619b17621b |
completed | May 2, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69f64caede108190a35cc7cbfead866f |
completed | May 2, 2026, 7:12 p.m. |
| PDg | Predicate description generation | batch_69f64e36c57c8190af09470a8d35512b |
completed | May 2, 2026, 7:19 p.m. |
Created at: April 28, 2026, 2:49 a.m.