Triple
T26697203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | early 1990s recession in the United States |
E673053
|
entity |
| Predicate | recoveryCharacterization |
P70548
|
FINISHED |
| Object | jobless recovery |
—
|
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: jobless recovery | Statement: [early 1990s recession in the United States, recoveryCharacterization, jobless recovery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recoveryCharacterization Context triple: [early 1990s recession in the United States, recoveryCharacterization, jobless recovery]
-
A.
resultCharacterization
chosen
Indicates how the outcome of an event, process, or action is qualitatively described or characterized.
-
B.
recovery
Indicates the process or state in which an entity regains a previous condition, function, or status after loss, damage, or decline.
-
C.
recoveryCapability
Indicates the ability of an entity to return to a normal or functional state after experiencing damage, failure, or disruption.
-
D.
studyCharacterization
Indicates a relationship where an entity conducts a detailed examination or analysis to characterize or define the properties, behavior, or features of another entity.
-
E.
designedToRecover
Indicates that something is intentionally created or configured for the purpose of regaining a prior state, condition, or resource after loss, damage, or failure.
- 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_69eecda2b49c8190a6c481cfc4c07954 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6177c7ddc8190b6c96e97be69030d |
completed | May 2, 2026, 3:25 p.m. |
| PD | Predicate disambiguation | batch_69f60b8bb0d08190ab5a9a2a8847c6f4 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:29 a.m.