Triple
T35540586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southampton–New York City |
E1027047
|
entity |
| Predicate | countryAtWesternTerminus |
P56159
|
FINISHED |
| Object | United States |
E14
|
NE 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: United States | Statement: [Southampton–New York City, countryAtWesternTerminus, United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryAtWesternTerminus Context triple: [Southampton–New York City, countryAtWesternTerminus, United States]
-
A.
westernTerminusCountry
chosen
Indicates the country in which the westernmost endpoint of something (such as a route, line, or feature) is located.
-
B.
westernTerminusAtBorderWith
Indicates that something’s western endpoint or final location lies at a border shared with another region or entity.
-
C.
isWesternmostPartOf
Indicates that one entity is the furthest to the west within the geographic extent or boundary of another entity.
-
D.
easternTerminusCountry
Indicates the country in which the eastern terminus (end point) of something, such as a route or infrastructure, is located.
-
E.
southernTerminusCountry
Indicates the country in which the southern endpoint or terminus of something (such as a route, line, or feature) is located.
- F. None of above.
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_69f76e008ba08190927acd8e5e0344c8 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a01d48f41f4819093a5b47288a073c1 |
completed | May 11, 2026, 1:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a386837a75c8190a2103302542050c6 |
completed | June 21, 2026, 10:39 p.m. |
| PD | Predicate disambiguation | batch_6a01d3fa278c8190838174dd96ef5dde |
completed | May 11, 2026, 1:04 p.m. |
Created at: May 3, 2026, 4:04 p.m.