Triple
T10951291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GEE-H |
E258731
|
entity |
| Predicate | hasModelFamily |
P57888
|
FINISHED |
| Object | Gee language models |
—
|
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: Gee language models | Statement: [GEE-H, hasModelFamily, Gee language models]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasModelFamily Context triple: [GEE-H, hasModelFamily, Gee language models]
-
A.
supportsModelFamily
chosen
Indicates that one entity provides compatibility, functionality, or resources necessary for the operation or use of a particular model family.
-
B.
hasModelSeries
Indicates a relationship where an item or product is associated with a specific model series it belongs to.
-
C.
hasVariantFamily
Indicates that one entity is related to another as a different version, type, or family variant of it.
-
D.
hasRepresentativeFamily
Indicates that an entity is associated with a particular family that serves as its representative or characteristic example.
-
E.
containsFamily
Indicates that one entity includes or encompasses members of a particular family group within it.
- 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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770fc156c8190826e124c13ce7242 |
completed | April 9, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69d72e874f48819096ffa878f90c7d5b |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:23 p.m.