Triple
T35922865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Francis Dam disaster |
E1038932
|
entity |
| Predicate | timeOfDamFailure |
P140232
|
FINISHED |
| Object | 1928-03-12T23:57 |
—
|
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: 1928-03-12T23:57 | Statement: [St. Francis Dam disaster, timeOfDamFailure, 1928-03-12T23:57]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfDamFailure Context triple: [St. Francis Dam disaster, timeOfDamFailure, 1928-03-12T23:57]
-
A.
dikeBreaches
Indicates that a dike fails or ruptures, allowing water to break through its barrier.
-
B.
typeOfDam
Indicates the specific kind or classification of a dam associated with an entity.
-
C.
completionOfAssociatedDam
Indicates the completion status or occurrence of finishing construction or development of a related dam.
-
D.
laterDamCompletionDate
Indicates that one dam’s completion date occurs chronologically after another dam’s completion date.
-
E.
ruptureDate
chosen
Indicates the date on which a rupture event (such as a break, burst, or failure) occurs in the relationship between entities.
- 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_69f76e2320748190b7f5c4750d0cd0d3 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fdbaa226708190b8ed96e93aad38de |
completed | May 8, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_69fdb58b07e48190837e00966de050d4 |
completed | May 8, 2026, 10:06 a.m. |
Created at: May 3, 2026, 4:07 p.m.