Triple
T18589056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walther P38-style pistol (G1) |
E454310
|
entity |
| Predicate | toyCategory |
P92657
|
FINISHED |
| Object | action figure accessory |
—
|
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: action figure accessory | Statement: [Walther P38-style pistol (G1), toyCategory, action figure accessory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: toyCategory Context triple: [Walther P38-style pistol (G1), toyCategory, action figure accessory]
-
A.
toyType
chosen
Indicates the specific category or kind of toy that an item belongs to.
-
B.
primaryToy
Indicates that one entity is the main or most frequently used toy associated with another entity.
-
C.
toyLine
Indicates that one entity is part of, or associated with, a particular toy product line or series.
-
D.
toyTreatment
Indicates a relationship where one entity applies a treatment, procedure, or intervention to a toy or toy-like object.
-
E.
toySystem
Indicates a relationship where something functions as or belongs to a toy system, typically a simplified or illustrative version of a larger or more complex system.
- F. None of above.
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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e545b3e564819088e60fc25d1976f0 |
completed | April 19, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69e478c98d4c81909d37a0e72c6e7bd0 |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:44 a.m.