Triple
T24529593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Poso Oil Field |
E606764
|
entity |
| Predicate | isOnshoreFieldIn |
P140131
|
FINISHED |
| Object | California Central Valley |
—
|
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: California Central Valley | Statement: [Mount Poso Oil Field, isOnshoreFieldIn, California Central Valley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOnshoreFieldIn Context triple: [Mount Poso Oil Field, isOnshoreFieldIn, California Central Valley]
-
A.
onshoreOrOffshore
Indicates whether something is located or occurring on land (onshore) or at sea/away from land (offshore).
-
B.
isInlandFrom
Indicates that one place lies away from the coast, further toward the interior of the land, relative to another place.
-
C.
isInInlandArea
chosen
Indicates that one entity is located within an inland area, away from coastal or marine regions.
-
D.
isInLand
Indicates that one entity is located within the geographical boundaries of a land area or territory of another entity.
-
E.
isOutgroundOf
Indicates that one entity lies outside the boundary, extent, or coverage area defined by another entity.
- 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_69e2c4c90c848190b23c4303620dcaaf |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:25 a.m.