Triple
T28056920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google Boulder campus |
E708990
|
entity |
| Predicate | supportsWorkModel |
P137919
|
FINISHED |
| Object | collaborative work |
—
|
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: collaborative work | Statement: [Google Boulder campus, supportsWorkModel, collaborative work]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsWorkModel Context triple: [Google Boulder campus, supportsWorkModel, collaborative work]
-
A.
supportedWork
Indicates that one entity provides assistance, resources, or endorsement to enable or sustain the work or activity of another entity.
-
B.
supportedModel
chosen
Indicates that one entity provides compatibility with, or operational backing for, a particular model.
-
C.
supportedByWork
Indicates that one entity’s existence, validity, or outcome is backed, justified, or enabled by the work or efforts of another entity.
-
D.
supportsContributionModel
Indicates that one entity enables or is compatible with a particular model or framework for making contributions (such as donations, content, or resources).
-
E.
supportedWorksBy
Indicates that certain works (such as projects, products, or activities) are backed, endorsed, or enabled by a particular entity.
- 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_69ef9b6df9f48190bbb971d02cbe1b65 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_6a0058c341ac8190825067dc25158839 |
completed | May 10, 2026, 10:06 a.m. |
| PD | Predicate disambiguation | batch_6a005857249c81908b27587b84d84dbb |
completed | May 10, 2026, 10:05 a.m. |
Created at: April 27, 2026, 8:37 p.m.