Triple
T26302912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingston coal ash spill of 2008 |
E661604
|
entity |
| Predicate | impactedCommunity |
P65945
|
FINISHED |
| Object | Kingston, Tennessee |
—
|
NE NERFINISHED |
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: Kingston, Tennessee | Statement: [Kingston coal ash spill of 2008, impactedCommunity, Kingston, Tennessee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: impactedCommunity Context triple: [Kingston coal ash spill of 2008, impactedCommunity, Kingston, Tennessee]
-
A.
influencesCommunity
chosen
Indicates that one entity has an effect on the behavior, attitudes, or conditions of a community.
-
B.
notableCommunityAffected
Indicates that a particular community of notable significance is directly impacted or influenced by the subject.
-
C.
includesCommunity
Indicates that one entity encompasses, contains, or has within it a particular community as part of its scope or composition.
-
D.
representedCommunitiesIn
Indicates that an entity acted on behalf of or served as a representative for certain communities within a given context or domain.
-
E.
eligibleCommunity
Indicates that a community meets the required criteria or conditions to qualify for a specified program, benefit, or status.
- 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_69ee812cd48c81908054068f545f0526 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c1f94ac8190bc6fbc7916fc0d82 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 26, 2026, 10:17 p.m.