Triple
T36531249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kearny Connection |
E900448
|
entity |
| Predicate | previousTerminusBeforeOpening |
P200585
|
FINISHED |
| Object | Hoboken Terminal |
—
|
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: Hoboken Terminal | Statement: [Kearny Connection, previousTerminusBeforeOpening, Hoboken Terminal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousTerminusBeforeOpening Context triple: [Kearny Connection, previousTerminusBeforeOpening, Hoboken Terminal]
-
A.
openedAsTerminus
Indicates that a transportation line or route was initially opened with this location serving as its end-point terminus.
-
B.
administrationBeforeOpening
Indicates that an administrative process or action must occur prior to the opening or commencement of another event or state.
-
C.
closedBefore
Indicates that one entity was closed at an earlier time than another entity.
-
D.
predecessorOpeningDate
Indicates that the subject entity’s opening date occurs before the opening date of another, predecessor entity.
-
E.
operatorAtOpening
Indicates that an operator is present and on duty at the time of an opening event.
- 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_69f76e5fbb388190b70c4c15573c8143 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff97637ad881908c24fe2cc6b036db |
completed | May 9, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69ff96c43a808190942eeda1934602db |
completed | May 9, 2026, 8:19 p.m. |
| PDg | Predicate description generation | batch_69ff976281888190a2e872296fb4a661 |
completed | May 9, 2026, 8:21 p.m. |
Created at: May 3, 2026, 4:11 p.m.