Triple
T31851671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TensorFlow GraphDef |
E813079
|
entity |
| Predicate | protoDefinitionLocation |
P55178
|
FINISHED |
| Object | tensorflow/core/framework/graph.proto |
—
|
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: tensorflow/core/framework/graph.proto | Statement: [TensorFlow GraphDef, protoDefinitionLocation, tensorflow/core/framework/graph.proto]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protoDefinitionLocation Context triple: [TensorFlow GraphDef, protoDefinitionLocation, tensorflow/core/framework/graph.proto]
-
A.
definesLocation
Indicates that one entity specifies or establishes the spatial or geographic position of another entity.
-
B.
implementationLocation
Indicates the place or environment where something is implemented, carried out, or put into effect.
-
C.
metadataLocation
Indicates the location or source where descriptive or administrative information about an entity is stored or can be accessed.
-
D.
documentationLocation
chosen
Indicates the place or resource where relevant documentation for an entity can be found.
-
E.
positionOnDefinitions
Indicates the stance or viewpoint an entity holds regarding the definitions or conceptual formulations of a term, idea, or issue.
- 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_69f348eb327881909b4584b925742f6e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b03e438c81909ff3b98edd72ae38 |
completed | May 3, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:51 p.m.