Triple
T29108386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Differentiable Neural Computers |
E736824
|
entity |
| Predicate | readOperation |
P93409
|
FINISHED |
| Object | weighted sum of memory rows |
—
|
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: weighted sum of memory rows | Statement: [Differentiable Neural Computers, readOperation, weighted sum of memory rows]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: readOperation Context triple: [Differentiable Neural Computers, readOperation, weighted sum of memory rows]
-
A.
readBy
Indicates that a particular text, document, or content item has been read or consumed by a specific person or agent.
-
B.
readReturns
chosen
Indicates that an entity returns or provides the result or output of a read operation on another entity.
-
C.
readWith
Indicates that one entity engages in reading an item together with another entity, implying a shared or joint reading activity.
-
D.
readsFrom
Indicates that one entity obtains or accesses data, information, or content from another entity as a source.
-
E.
readBehavior
Indicates that one entity engages in the act or manner of reading something, capturing how that reading is performed or characterized.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f661bc4db08190bd91745a1ebfc2ae |
completed | May 2, 2026, 8:42 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:17 a.m.