Triple
T24483244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Massachusetts Clean Water Trust |
E617434
|
entity |
| Predicate | projectTypeFinanced |
P39623
|
FINISHED |
| Object | drinking water treatment facilities |
—
|
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: drinking water treatment facilities | Statement: [Massachusetts Clean Water Trust, projectTypeFinanced, drinking water treatment facilities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: projectTypeFinanced Context triple: [Massachusetts Clean Water Trust, projectTypeFinanced, drinking water treatment facilities]
-
A.
eligibleProjectType
Indicates that a project belongs to a category or type that qualifies it for a specific program, process, or benefit.
-
B.
funderType
Indicates the category or kind of organization or individual that provides funding in the relationship.
-
C.
notableProjectType
Indicates the type or category of a project for which an entity is particularly well-known or notable.
-
D.
typicalProjectTypes
Indicates the kinds or categories of projects that are most commonly or characteristically associated with a given entity.
-
E.
typeOfProject
chosen
Indicates the specific category or kind of project that an entity is associated with or classified under.
- 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_69e2d7f3ae788190b683394db15f220e |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2a9d912e88190bc39c05a9d7f407e |
completed | April 30, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69f2a6a4580481908fddc385f5262f95 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:21 a.m.