Triple
T13106615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MAS Program |
E310858
|
entity |
| Predicate | enablesPurchasesBy |
P77223
|
FINISHED |
| Object | federal agencies |
—
|
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: federal agencies | Statement: [MAS Program, enablesPurchasesBy, federal agencies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enablesPurchasesBy Context triple: [MAS Program, enablesPurchasesBy, federal agencies]
-
A.
eligiblePurchasers
chosen
Indicates that certain entities are permitted or qualified to make a particular purchase under specified rules or conditions.
-
B.
isPurchasedBy
Indicates that one entity is bought or acquired in a transaction by another entity.
-
C.
canBePurchasedWith
Indicates that one entity is able to be bought or acquired using another entity as the form of payment.
-
D.
requiresPurchaserStatus
Indicates that performing this action or entering into this relationship is contingent on the entity having purchaser status.
-
E.
hasInAppPurchases
Indicates that an application offers additional content, features, or services that users can buy from within the app itself.
- 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_69d806a872d08190a329806f8ff30df4 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98154c9f48190aeca779d97151759 |
completed | April 10, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69d98041a3548190a05ddd83dbb660fa |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 9:05 p.m.