Triple
T15809247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2010 San Bruno pipeline explosion |
E383301
|
entity |
| Predicate | typeOfPipeline |
P120165
|
FINISHED |
| Object | high-pressure transmission pipeline |
—
|
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: high-pressure transmission pipeline | Statement: [2010 San Bruno pipeline explosion, typeOfPipeline, high-pressure transmission pipeline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfPipeline Context triple: [2010 San Bruno pipeline explosion, typeOfPipeline, high-pressure transmission pipeline]
-
A.
processType
Indicates the specific kind or category of process that an entity or activity belongs to.
-
B.
typeOfCluster
Indicates that one entity is classified as a specific kind or category of cluster in relation to another entity.
-
C.
typeOfState
Indicates that one state is a specific kind or category of another, more general state.
-
D.
typeOfCommand
Indicates that one entity is a specific kind or category of command in relation to another entity.
-
E.
pdsType
Indicates that an entity has or is classified by a specific Product Data Specification (PDS) type or category.
- 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_69d86da2858c819090cc8481e7207b6e |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0b529c6b481909664153ecc381f7c |
completed | April 16, 2026, 10:08 a.m. |
| PD | Predicate disambiguation | batch_69e0053b847c8190945726c3ddac21cc |
completed | April 15, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69e00e48d49c819081afccb02f9cf18b |
completed | April 15, 2026, 10:16 p.m. |
Created at: April 10, 2026, 4:48 a.m.