Triple
T23403978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pennsylvania border |
E559583
|
entity |
| Predicate | hasSouthernNeighbor |
P117551
|
FINISHED |
| Object | Maryland |
—
|
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: Maryland | Statement: [Pennsylvania border, hasSouthernNeighbor, Maryland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSouthernNeighbor Context triple: [Pennsylvania border, hasSouthernNeighbor, Maryland]
-
A.
hasSouthBorder
chosen
Indicates that one entity shares its southern boundary or border with another entity.
-
B.
isOnSouthernPartOf
Indicates that one entity is located on the southern part or southern region of another entity.
-
C.
hasNorthNeighbor
Indicates that one entity is located directly to the north of another entity.
-
D.
hasNeighboringCountryToNorth
Indicates that one country is directly adjacent to and located south of another country, which lies to its north.
-
E.
hasSouthernTerminus
Indicates that one entity serves as the southern endpoint or terminus of another entity, such as a route, line, or path.
- 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_69e24549610c8190a069d6411ce5f661 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a4e16f9881908ea4bef465e3af11 |
completed | April 29, 2026, 6:27 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:37 p.m.