Triple
T9221562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castle Clinton |
E221371
|
entity |
| Predicate | ticketOfficeFor |
P61741
|
FINISHED |
| Object | ferries to Statue of Liberty |
—
|
LITERAL 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: ferries to Statue of Liberty | Statement: [Castle Clinton, ticketOfficeFor, ferries to Statue of Liberty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ticketOfficeFor Context triple: [Castle Clinton, ticketOfficeFor, ferries to Statue of Liberty]
-
A.
ticketOfTarget
Indicates that one entity is a ticket associated with, or issued for, a specific target entity.
-
B.
ticketClass
Indicates the category or level of service assigned to a ticket within a ticketing or reservation system.
-
C.
ticketClassSystem
Indicates that an entity is classified within a particular ticketing or fare class system that defines categories or levels of tickets.
-
D.
ticketDemand
Indicates that there is a level of desire or need among potential buyers for tickets to an event, service, or offering.
-
E.
ticketMachines
chosen
Indicates that there is a relationship involving ticket machines, typically denoting where they are located, available, or associated with a particular entity or place.
- 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_69ca83eae42c8190a0ea9e040710a277 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda76e3648190af9e24381db7679a |
completed | April 1, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69cc7a3daeb481908b0abde3fbc1f1f0 |
completed | April 1, 2026, 1:51 a.m. |
Created at: March 30, 2026, 7:28 p.m.