Triple
T22146425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Van Ness station |
E547298
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Market Street |
—
|
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: Market Street | Statement: [Van Ness station, locatedOn, Market Street]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Market Street Context triple: [Van Ness station, locatedOn, Market Street]
-
A.
Market Street
Market Street is a social network game developed by Playdom in which players manage and grow their own virtual retail shops.
-
B.
Market Street
Market Street is a major east–west thoroughfare in Philadelphia known for its commercial activity, transit connections, and role as a central artery of the city.
-
C.
Market Street
Market Street is a common street name typically referring to a central thoroughfare historically used as a marketplace in many towns and cities.
-
D.
Market Street
chosen
Market Street is a major commercial thoroughfare in the Sydney central business district, known for its shopping precincts and proximity to landmarks such as Sydney Tower.
-
E.
Market Street
Market Street is a primary thoroughfare running through downtown St. Louis, Missouri, lined with civic buildings, businesses, and cultural landmarks.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e3a95d88190a3bd80d9471976c3 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129f097248190a8a3cdff1593b5b5 |
completed | April 28, 2026, 9:43 p.m. |
Created at: April 16, 2026, 8:33 p.m.