Triple
T13683636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York State Mitchell-Lama Housing Program |
E328062
|
entity |
| Predicate | usesIncentive |
P111157
|
FINISHED |
| Object | subsidies |
—
|
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: subsidies | Statement: [New York State Mitchell-Lama Housing Program, usesIncentive, subsidies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesIncentive Context triple: [New York State Mitchell-Lama Housing Program, usesIncentive, subsidies]
-
A.
providesIncentivesTo
Indicates that one entity offers rewards, benefits, or motivations to another entity to encourage a desired behavior or outcome.
-
B.
offersIncentive
Indicates that one entity provides a reward, benefit, or motivation to another entity to encourage a specific action or behavior.
-
C.
usesPromotion
Indicates that an entity applies or takes advantage of a specific promotion, discount, or special offer.
-
D.
typeOfIncentive
Indicates the specific kind or category of incentive associated with an entity or action.
-
E.
ownerIncentive
Indicates that an owner has a motivation, benefit, or reward associated with a particular entity, action, or outcome.
- 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_69d8076f1fa8819094664a59b55010df |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc66e75188190a9e82fdc5eb26513 |
completed | April 12, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69dbbe9059488190a8113177c83e1481 |
completed | April 12, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69dbc59ca1a88190a6abd3bd00554c93 |
completed | April 12, 2026, 4:17 p.m. |
Created at: April 9, 2026, 9:53 p.m.