Triple
T5222214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Domestic Marshall Plan for American cities |
E117895
|
entity |
| Predicate | proposedSolutionType |
P4453
|
FINISHED |
| Object | large-scale public investment |
—
|
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: large-scale public investment | Statement: [Domestic Marshall Plan for American cities, proposedSolutionType, large-scale public investment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: proposedSolutionType Context triple: [Domestic Marshall Plan for American cities, proposedSolutionType, large-scale public investment]
-
A.
solutionType
chosen
Indicates the specific category or kind of solution associated with an entity or problem.
-
B.
typeOfSupport
Indicates the kind or category of assistance, help, or backing provided in a given context.
-
C.
offersSolution
Indicates that one entity provides or proposes a remedy, answer, or way to resolve a problem or need experienced by another entity.
-
D.
typeOfProject
Indicates the specific category or kind of project that an entity is associated with or classified under.
-
E.
typeOfApplication
Indicates the specific category or kind of application involved in the relationship or action.
- 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_69bd4465e03081909bfcfd7113062590 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7aba05b48190b6a7fc52ab3532f0 |
completed | March 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69bd77bd2a448190a9ae5afd2585a7b9 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:48 p.m.