Triple
T33585158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Motors Corporation |
E860258
|
entity |
| Predicate | acquisitionDateByChrysler |
P15703
|
FINISHED |
| Object | 1987 |
—
|
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: 1987 | Statement: [American Motors Corporation, acquisitionDateByChrysler, 1987]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acquisitionDateByChrysler Context triple: [American Motors Corporation, acquisitionDateByChrysler, 1987]
-
A.
acquisitionDate
Indicates the date on which one entity formally acquires or takes ownership of another entity.
-
B.
yearDeliveredApprox
Indicates that the year an item or entity was delivered is known only approximately, rather than as an exact calendar year.
-
C.
wasAcquiredIn
Indicates that one entity obtained ownership or control of another entity through an acquisition event that occurred at a specific time or in a specific transaction.
-
D.
acquisitionCompletedYear
chosen
Indicates the calendar year in which an acquisition transaction was fully completed.
-
E.
yearFirstDelivered
Indicates the calendar year in which something (such as a product, service, or item) was first delivered or made available.
- 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_69f3497e70e48190951c94d072879bec |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6ffbad8848190867c2988c0ceb84f |
completed | May 3, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69f6fc5740fc81909774a4f65201a3ff |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:40 a.m.