Triple
T17935918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ka-Bar Knives |
E448464
|
entity |
| Predicate | hasBrand |
P1500
|
FINISHED |
| Object | KA-BAR |
—
|
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: KA-BAR | Statement: [Ka-Bar Knives, hasBrand, KA-BAR]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KA-BAR Context triple: [Ka-Bar Knives, hasBrand, KA-BAR]
-
A.
Ka-Bar Knives
chosen
Ka-Bar Knives is an American knife manufacturer best known for its iconic combat and utility knives originally designed for the U.S. military.
-
B.
Puma Knives
Puma Knives is a renowned German manufacturer of high-quality hunting and outdoor knives, traditionally associated with the knife-making city of Solingen.
-
C.
Leatherman
Leatherman is a song by the American rock band Pearl Jam, released as a B-side and known for its acoustic-driven sound and storytelling lyrics.
-
D.
SOG
SOG is the station code for South Orange, a commuter rail station in New Jersey served by NJ Transit.
-
E.
Diemaco
Diemaco is a Canadian firearms manufacturer best known for producing and developing variants of the AR-15/M16 family of rifles for military and law enforcement use.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4ad924f6c8190a0d676dfa20c9918 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, 10:21 a.m.