Triple
T32191535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Universal Studios backlot |
E822266
|
entity |
| Predicate | hasStreetSet |
P72421
|
FINISHED |
| Object | New York 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: New York Street | Statement: [Universal Studios backlot, hasStreetSet, New York Street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStreetSet Context triple: [Universal Studios backlot, hasStreetSet, New York Street]
-
A.
hasStreet
Indicates that an entity is located on, associated with, or identified by a particular street.
-
B.
hasStreetLevel
Indicates that something is located at, accessible from, or directly associated with the street level of a building or area.
-
C.
hasNumberOfStreets
Indicates the relationship that specifies how many streets are associated with or contained within a given entity.
-
D.
hasStreetPresence
Indicates that an entity maintains a visible, active, or influential presence in public urban spaces or streets.
-
E.
streetSet
chosen
Indicates that a particular street belongs to, or is included within, a specified set or collection of streets.
- 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_69f3490819cc81909bae1f8ce99423c5 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fef112398081909237c3872345968b |
completed | May 9, 2026, 8:32 a.m. |
| PD | Predicate disambiguation | batch_69feefb14ec08190ab401987d8c84a23 |
completed | May 9, 2026, 8:26 a.m. |
Created at: May 1, 2026, 12:35 a.m.