Triple
T37057986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcellus Shale |
E917246
|
entity |
| Predicate | underliesRegion |
P123914
|
FINISHED |
| Object | Pennsylvania |
—
|
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: Pennsylvania | Statement: [Marcellus Shale, underliesRegion, Pennsylvania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underliesRegion Context triple: [Marcellus Shale, underliesRegion, Pennsylvania]
-
A.
underliesArea
chosen
Indicates that one entity forms the foundational basis or underlying support for a particular area or domain of activity, knowledge, or influence.
-
B.
isRegionOf
Indicates that one entity is a geographic or administrative region belonging to, contained within, or associated with another entity.
-
C.
hasRegionBehind
Indicates that one region is spatially located behind another region relative to a given viewpoint or reference frame.
-
D.
suppliedRegion
Indicates that one entity serves as the geographic or administrative region from which another entity receives its supply or resources.
-
E.
hasRegion
Indicates that an entity includes, contains, or is associated with a specific geographic or administrative region as part of its scope or structure.
- 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_69f76e95fa40819091e14681087ae5e4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd91a5dad8819093eeeef527027890 |
completed | May 8, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69fd8f65fe9081908902500a3228d935 |
completed | May 8, 2026, 7:23 a.m. |
Created at: May 3, 2026, 4:14 p.m.