Triple
T20803120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ENE |
E512088
|
entity |
| Predicate | associatedCompanyImpact |
P45127
|
FINISHED |
| Object | losses for shareholders |
—
|
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: losses for shareholders | Statement: [ENE, associatedCompanyImpact, losses for shareholders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedCompanyImpact Context triple: [ENE, associatedCompanyImpact, losses for shareholders]
-
A.
affectedCompany
Indicates that a company is impacted or influenced by a particular event, action, or entity.
-
B.
associatedCompanyAction
Indicates that an action is performed by, on behalf of, or in direct connection with a particular company.
-
C.
associatedCompanyFate
Indicates that there is a relationship between an entity and the outcome or final status (e.g., closure, acquisition, bankruptcy) of a company with which it is or was associated.
-
D.
associatedConflictImpact
Indicates a relationship where an entity is linked to a specific conflict and the effects or consequences that conflict has on it.
-
E.
impactOnBusiness
chosen
Indicates the effect or influence that one factor, event, or action has on a business’s performance, operations, or outcomes.
- 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2b2d5688190aaa58a2594d4787c |
completed | April 21, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69e5c99ca55481908e8d434fa901cfd6 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:39 p.m.