Triple
T22719008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Urban Homesteading program |
E561809
|
entity |
| Predicate | incentive |
P79344
|
FINISHED |
| Object | acquisition of homes at little or no cost |
—
|
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: acquisition of homes at little or no cost | Statement: [Urban Homesteading program, incentive, acquisition of homes at little or no cost]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: incentive Context triple: [Urban Homesteading program, incentive, acquisition of homes at little or no cost]
-
A.
typeOfIncentive
Indicates the specific kind or category of incentive associated with an entity or action.
-
B.
providesIncentivesTo
chosen
Indicates that one entity offers rewards, benefits, or motivations to another entity to encourage a desired behavior or outcome.
-
C.
ownerIncentive
Indicates that an owner has a motivation, benefit, or reward associated with a particular entity, action, or outcome.
-
D.
usesIncentive
Indicates that one entity employs or applies an incentive (such as a reward, benefit, or motivation) to influence the behavior or decisions of another entity.
-
E.
qualificationIncentive
Indicates that an incentive or benefit is provided contingent upon obtaining or holding a particular qualification.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790fbf9c819082ba7b48801a7b39 |
completed | April 29, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69eed2a971c0819088af574e40c9343f |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:19 p.m.