Triple
T17521002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TensorFlow SavedModel (via conversion) |
E426677
|
entity |
| Predicate | inputFormatOf |
P80182
|
FINISHED |
| Object | TensorFlow.js Layers model format |
—
|
NE NERFINISHED |
How this triple was built (3 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.js Layers model format | Statement: [TensorFlow SavedModel (via conversion), inputFormatOf, TensorFlow.js Layers model format]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TensorFlow.js Layers model format Context triple: [TensorFlow SavedModel (via conversion), inputFormatOf, TensorFlow.js Layers model format]
-
A.
TensorFlow.js
chosen
TensorFlow.js is a JavaScript library that enables training and running machine learning models directly in the browser and in Node.js using TensorFlow.
-
B.
TensorFlow Model Analysis
TensorFlow Model Analysis is an open-source library for evaluating, validating, and monitoring machine learning models—especially at scale and on large datasets—within TensorFlow-based pipelines.
-
C.
TensorFlow Serving
TensorFlow Serving is a flexible, high-performance system for deploying and serving machine learning models in production, particularly those built with TensorFlow.
-
D.
TensorFlow Transform
TensorFlow Transform is a TensorFlow-based library for performing scalable, full-pass data preprocessing and feature engineering that can be applied consistently in both training and serving.
-
E.
NNEF
NNEF (Neural Network Exchange Format) is an open standard from the Khronos Group designed to enable portable, efficient interchange of trained neural network models across different hardware and software platforms.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inputFormatOf Context triple: [TensorFlow SavedModel (via conversion), inputFormatOf, TensorFlow.js Layers model format]
-
A.
packageFormat
Indicates the format or type in which a package is structured, encoded, or delivered.
-
B.
definesFormatFor
chosen
Indicates that one entity specifies or establishes the format or structural pattern to be used by another entity.
-
C.
operatesInFormat
Indicates that an entity functions, performs its role, or is carried out using a specified format.
-
D.
isPrimaryFormatFor
Indicates that one format is the main or default format used to represent or distribute another related entity.
-
E.
usedFormat
Indicates that one entity employs or applies a particular format or representation in relation to another 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_69d889de677081909b22d2657b1f0292 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e452d23cf08190925510344fa36f57 |
completed | April 19, 2026, 3:58 a.m. |
| PD | Predicate disambiguation | batch_69e3b4f8b9888190aa8a45e09acf4319 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:49 a.m.