Triple
T17005138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thrift Savings Plan |
E412549
|
entity |
| Predicate | distributionOptions |
P73617
|
FINISHED |
| Object | lump-sum payments |
—
|
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: lump-sum payments | Statement: [Thrift Savings Plan, distributionOptions, lump-sum payments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distributionOptions Context triple: [Thrift Savings Plan, distributionOptions, lump-sum payments]
-
A.
distributionBy
Indicates how something is allocated, arranged, or spread according to a specified criterion or grouping.
-
B.
distributionAvailability
Indicates that a product or resource is available for distribution through a particular channel, location, or method.
-
C.
distribution
Indicates the act or pattern of giving, delivering, or spreading something from one source to multiple recipients or locations.
-
D.
distributionIncludes
chosen
Indicates that a distribution or release of something contains or encompasses the specified item or component.
-
E.
distributionName
Indicates the name or title assigned to a particular distribution or release of something.
- 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d382400c819092ec0ca0de815888 |
completed | April 18, 2026, 6:54 p.m. |
| PD | Predicate disambiguation | batch_69e35d552bc08190af17ef7659e094ef |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:32 a.m.