Triple
T30315681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | iMac Pro (2017) |
E771048
|
entity |
| Predicate | hasT2Chip |
P168049
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [iMac Pro (2017), hasT2Chip, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasT2Chip Context triple: [iMac Pro (2017), hasT2Chip, yes]
-
A.
hasChipType
chosen
Indicates that an entity is associated with or uses a specific type or category of chip.
-
B.
hasOnChip
Indicates that one component or system includes another component integrated directly onto the same chip or integrated circuit.
-
C.
supportsOnChipNetworking
Indicates that one entity provides or enables integrated networking capabilities directly on a chip for another entity.
-
D.
companionChip
Indicates that one entity serves as a companion or auxiliary chip to another, typically functioning alongside it to provide additional or supporting capabilities.
-
E.
hasTwinFeature
Indicates that two entities share an identical or nearly identical feature, characteristic, or component, as if they are twins in that respect.
- 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_69f22488f224819081b0f3ec41ab975c |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68193b2b08190a00f08dbba490563 |
completed | May 2, 2026, 10:58 p.m. |
| PD | Predicate disambiguation | batch_69f67603526c81908295a1ece8727c66 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:51 p.m.