Triple
T17023032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AVIDAC |
E412991
|
entity |
| Predicate | influencedBy |
P9
|
FINISHED |
| Object | IAS machine |
E87767
|
NE 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: IAS machine | Statement: [AVIDAC, influencedBy, IAS machine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IAS machine Context triple: [AVIDAC, influencedBy, IAS machine]
-
A.
IAS machine
chosen
The IAS machine was an early electronic stored-program computer designed by John von Neumann and his colleagues at the Institute for Advanced Study, serving as a prototype for many subsequent computer architectures.
-
B.
Isa Machine
Isa Machine is the stage name of Isabella Summers, the English musician, producer, and keyboardist best known as a founding member of Florence + The Machine.
-
C.
NuMachine
NuMachine was an early 1980s experimental workstation computer project at MIT that pioneered the NuBus expansion bus architecture.
-
D.
the Machine
The Machine is a notorious torture device from "The Princess Bride" that painfully drains years of life from its victims.
-
E.
Intelligence Processing Unit
The Intelligence Processing Unit is a specialized processor architecture designed by Graphcore to accelerate artificial intelligence and machine learning workloads with highly parallel, memory-rich compute.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d2abbc81908943becf5f539fc6 |
completed | April 18, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012334c3b48190b125ab926450c45b |
completed | May 11, 2026, 12:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.