Triple
T35759846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | B6500 |
E1033541
|
entity |
| Predicate | vendorPositioning |
P5254
|
FINISHED |
| Object | competitor to IBM System/360 |
—
|
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: competitor to IBM System/360 | Statement: [B6500, vendorPositioning, competitor to IBM System/360]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vendorPositioning Context triple: [B6500, vendorPositioning, competitor to IBM System/360]
-
A.
platformPosition
Indicates the relative location or placement of something on, within, or in relation to a platform.
-
B.
venueFlagship
Indicates that a venue serves as the primary or flagship location within a brand, organization, or chain.
-
C.
brandPositioning
chosen
Indicates how a brand is strategically placed and perceived in the minds of its target audience relative to competitors.
-
D.
positionOnBusiness
Indicates the stance, role, or viewpoint an entity holds regarding a particular business, company, or commercial matter.
-
E.
designPositioning
Indicates the spatial or conceptual placement of a design element relative to other elements or a defined reference.
- 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_69f76e1262f48190a313318665acc189 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a1c38ea08190933b631b316cf1b7 |
completed | May 3, 2026, 7:28 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:06 p.m.