Triple
T562922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Macintosh 128K |
E13491
|
entity |
| Predicate | discontinuedDate |
P14100
|
FINISHED |
| Object | 1984-10-01 |
—
|
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: 1984-10-01 | Statement: [Macintosh 128K, discontinuedDate, 1984-10-01]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discontinuedDate Context triple: [Macintosh 128K, discontinuedDate, 1984-10-01]
-
A.
discontinuedIn
Indicates that an item, product, or service stopped being produced, offered, or supported starting in a specified time or place.
-
B.
discontinuedModel
Indicates that a particular model is no longer produced, sold, or officially supported.
-
C.
decommissionedDate
chosen
Indicates the date on which an entity was formally taken out of service or retired from active use.
-
D.
deFactoEndDate
Indicates the date on which a relationship, status, or condition effectively ended in practice, regardless of any formal or official end date.
-
E.
decommissionedReason
Indicates the reason or cause for which an entity, typically an asset or system, was taken out of service or formally retired.
- 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_69a4933edcf08190b35ecfd6014caee6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49a712bc48190ba298b3c76ab11cc |
completed | March 1, 2026, 7:58 p.m. |
| PD | Predicate disambiguation | batch_69a494c044648190a98589ab18935216 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.