Triple
T2857850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flint water crisis |
E63245
|
entity |
| Predicate | waterSourceRestored |
P43697
|
FINISHED |
| Object | Detroit water system |
—
|
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: Detroit water system | Statement: [Flint water crisis, waterSourceRestored, Detroit water system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterSourceRestored Context triple: [Flint water crisis, waterSourceRestored, Detroit water system]
-
A.
waterSource
Indicates that one entity serves as the source or provider of water for another entity.
-
B.
waterSourceDedicatedTo
Indicates that a particular water source is specifically allocated or reserved for a designated use, group, or purpose.
-
C.
waterSourceType
Indicates the kind or category of source from which water is obtained.
-
D.
sourceOfWaterSupply
Indicates that one entity serves as the origin or provider of another entity’s water supply.
-
E.
waterOrigin
Indicates the source or starting location from which the water originates or is supplied.
- 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_69ab4c41e8c08190a9e8f5249cc12610 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf89d3b4819086936f26d8683a2a |
completed | March 7, 2026, 8:19 a.m. |
| PD | Predicate disambiguation | batch_69abdd10aef88190b750aae07e7df4dc |
completed | March 7, 2026, 8:08 a.m. |
| PDg | Predicate description generation | batch_69abdee94c2081908e5075e87e70780a |
completed | March 7, 2026, 8:16 a.m. |
Created at: March 6, 2026, 10:02 p.m.