Triple
T27155393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pennsylvania–Delaware border |
E682505
|
entity |
| Predicate | centerOfArc |
P163474
|
FINISHED |
| Object | New Castle, Delaware |
—
|
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: New Castle, Delaware | Statement: [Pennsylvania–Delaware border, centerOfArc, New Castle, Delaware]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centerOfArc Context triple: [Pennsylvania–Delaware border, centerOfArc, New Castle, Delaware]
-
A.
centerIs
Indicates that one entity serves as the central point or middle position of another entity or space.
-
B.
formsArcOf
Indicates that one entity curves around or spans between points so as to create an arc in relation to another entity.
-
C.
centerOfOrigin
Indicates the place or region where something (such as a species, product, idea, or movement) originally began or was first developed.
-
D.
relatedTriangleCenter
Indicates that one geometric entity is associated with a specific triangle center (such as centroid, incenter, circumcenter, etc.) of a given triangle.
-
E.
centeredDisc
Indicates that one disc-shaped object is positioned with its center aligned to a specified reference point or object.
- 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_69eefaceb2a08190b9659b7f730629f5 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f638d11c988190af7fd4572b08e038 |
completed | May 2, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69f63709e4848190b5cf322e06b23fb6 |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f638344b148190bf0414ef7c5f1f38 |
completed | May 2, 2026, 5:45 p.m. |
Created at: April 27, 2026, 9:16 a.m.