Triple
T309314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercury |
E6367
|
entity |
| Predicate | reasonForDiscontinuation |
P11350
|
FINISHED |
| Object | declining sales |
—
|
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: declining sales | Statement: [Mercury, reasonForDiscontinuation, declining sales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForDiscontinuation Context triple: [Mercury, reasonForDiscontinuation, declining sales]
-
A.
suspensionReason
Indicates the reason or cause for which an entity has been suspended from a status, activity, or service.
-
B.
cancellationReason
Indicates the reason or cause for which a previously scheduled or planned action, event, or agreement was canceled.
-
C.
reasonForDecline
Indicates the explanation or cause given for why something was rejected, reduced, or not accepted.
-
D.
discontinuedIn
Indicates that an item, product, or service stopped being produced, offered, or supported starting in a specified time or place.
-
E.
reasonForEndOfTerm
Indicates the specific cause or circumstance that led to the termination or conclusion of a term, position, or period of service.
- F. None of above. chosen
Provenance (4 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_69a2e79230508190b912ecb555aae17e |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea33ba688190b30d285cd7aa0d82 |
completed | Feb. 28, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69a2e93f38308190b4b480c951f1a1c3 |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea2af1388190b93235602ace679e |
completed | Feb. 28, 2026, 1:14 p.m. |
Created at: Feb. 28, 2026, 1:06 p.m.