Triple
T22280750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bowie knife |
E550722
|
entity |
| Predicate | mayHaveEdgeType |
P88169
|
FINISHED |
| Object | partially serrated edge |
—
|
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: partially serrated edge | Statement: [Bowie knife, mayHaveEdgeType, partially serrated edge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayHaveEdgeType Context triple: [Bowie knife, mayHaveEdgeType, partially serrated edge]
-
A.
edgeType
chosen
Indicates the specific kind or category of connection that exists between two related entities.
-
B.
hasEdge
Indicates that there exists a direct connection or link (an edge) between two entities in a graph or network.
-
C.
hasArcType
Indicates that one entity is associated with, or characterized by, a specific type or category of arc.
-
D.
mayBeJointBetween
Indicates that two or more entities might potentially form or participate in a joint relationship, without asserting that the joint relationship definitely exists.
-
E.
mayHaveBranch
Indicates that an entity is permitted or able to possess one or more branches as part of its structure or organization.
- 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_69e11e44d538819097c6b8f333af3352 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f14eab4f848190b1a8ba70f9fb0581 |
completed | April 29, 2026, 12:19 a.m. |
| PD | Predicate disambiguation | batch_69e72ff0363081909f794d19c8a64837 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:40 p.m.