Triple
T22719023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Urban Homesteading program |
E561809
|
entity |
| Predicate | targetProblem |
P64698
|
FINISHED |
| Object | vacant government-owned housing |
—
|
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: vacant government-owned housing | Statement: [Urban Homesteading program, targetProblem, vacant government-owned housing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetProblem Context triple: [Urban Homesteading program, targetProblem, vacant government-owned housing]
-
A.
problemType
Indicates the specific category or classification of a problem within a defined problem space or system.
-
B.
typicalProblem
Indicates that a situation, issue, or obstacle is representative or characteristic of the usual problems encountered in a given context.
-
C.
aimsToSolve
Indicates an intention or purpose directed toward resolving, addressing, or eliminating a particular problem, challenge, or issue.
-
D.
problemStatement
Indicates that an entity presents, defines, or expresses a specific problem or issue to be addressed.
-
E.
targetConcern
chosen
Indicates that something is the specific issue, problem, or subject that is the focus of attention, action, or consideration.
- 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.