Triple
T36194888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penn Plaza |
E1047093
|
entity |
| Predicate | hasStreetAddressPattern |
P201954
|
FINISHED |
| Object | buildings numbered as Penn Plaza |
—
|
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: buildings numbered as Penn Plaza | Statement: [Penn Plaza, hasStreetAddressPattern, buildings numbered as Penn Plaza]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStreetAddressPattern Context triple: [Penn Plaza, hasStreetAddressPattern, buildings numbered as Penn Plaza]
-
A.
streetPatternIncludes
Indicates that a street pattern contains or incorporates a specified element, feature, or sub-pattern within its overall layout.
-
B.
hasStreet
Indicates that an entity is located on, associated with, or identified by a particular street.
-
C.
hasStreetNamingPattern
Indicates that there is a characteristic or systematic way in which streets are named in relation to a given entity.
-
D.
hasStreetPatternRelation
Indicates a relationship between two areas or locations based on the similarity, alignment, or structural correspondence of their street patterns.
-
E.
streetAddress
Indicates the specific location of an entity in terms of its numbered building and street name within a postal address.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00383e868c819098fd17e25fcbdb04 |
completed | May 10, 2026, 7:48 a.m. |
| PD | Predicate disambiguation | batch_6a0037cc59688190b7b9da939a413db3 |
completed | May 10, 2026, 7:46 a.m. |
| PDg | Predicate description generation | batch_6a00383d83c08190af7bc00f17affd97 |
completed | May 10, 2026, 7:48 a.m. |
Created at: May 3, 2026, 4:08 p.m.