Triple
T3505297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HBOS |
E74060
|
entity |
| Predicate | acquisitionContext |
P48594
|
FINISHED |
| Object | 2008 financial crisis |
—
|
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: 2008 financial crisis | Statement: [HBOS, acquisitionContext, 2008 financial crisis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acquisitionContext Context triple: [HBOS, acquisitionContext, 2008 financial crisis]
-
A.
acquisitionType
Indicates the specific kind or category of acquisition relationship that exists between entities (such as a company buying another company, assets, or a controlling stake).
-
B.
contextOf
Indicates that one entity provides the situational, informational, or environmental background within which another entity exists, occurs, or is interpreted.
-
C.
acquiredFor
Indicates that one entity obtained or purchased another entity specifically for the benefit, use, or purpose of a third entity.
-
D.
context
Indicates that one entity provides the surrounding circumstances, setting, or background within which another entity, event, or statement occurs or is interpreted.
-
E.
originContext
Indicates the situational or environmental circumstances from which an entity, event, or piece of information originates.
- 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbf38e988190998d722b95830411 |
completed | March 8, 2026, 6:12 p.m. |
| PD | Predicate disambiguation | batch_69adae0cd8b0819099da300af09880da |
completed | March 8, 2026, 5:12 p.m. |
| PDg | Predicate description generation | batch_69adaef1037c819082c7af949ec85360 |
completed | March 8, 2026, 5:16 p.m. |
Created at: March 8, 2026, 3:18 p.m.