Triple
T24627104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GM VSS-F platform |
E609572
|
entity |
| Predicate | predecessorPlatformFamily |
P44839
|
FINISHED |
| Object | GM Gamma platform |
—
|
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: GM Gamma platform | Statement: [GM VSS-F platform, predecessorPlatformFamily, GM Gamma platform]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorPlatformFamily Context triple: [GM VSS-F platform, predecessorPlatformFamily, GM Gamma platform]
-
A.
predecessorPlatformCode
Indicates that one platform’s code identifies a platform that directly preceded another in a sequence or version lineage.
-
B.
predecessorSystemType
Indicates that one system type functioned as the predecessor or earlier version to another system type.
-
C.
predecessorCpuArchitecture
Indicates that one CPU architecture directly precedes another in an evolutionary or historical development sequence.
-
D.
predecessorSystem
Indicates that one system existed or was in use before and was replaced or superseded by another system.
-
E.
predecessorFamily
chosen
Indicates that one family is the earlier or ancestral family from which another family descends or follows.
- 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_69e2c4d1d3708190a0f2dc6a3a8523bb |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6d0ab708190b2e3b94dd20ca76b |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:32 a.m.