Triple
T10224067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Kenzie |
E242654
|
entity |
| Predicate | homeNeighborhood |
P4813
|
FINISHED |
| Object | working-class Boston community |
—
|
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: working-class Boston community | Statement: [Patrick Kenzie, homeNeighborhood, working-class Boston community]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeNeighborhood Context triple: [Patrick Kenzie, homeNeighborhood, working-class Boston community]
-
A.
neighborhood
Indicates that one entity is located in close spatial proximity to another, typically within the same local area or district.
-
B.
hasNeighbourhood
chosen
Indicates that one entity is located within, or is associated with, a particular neighborhood area of another entity.
-
C.
formerNeighborhood
Indicates that an entity was previously located in or associated with a particular neighborhood but is no longer situated there.
-
D.
homeTo
Indicates that a place serves as the primary location, residence, or habitat for a person, group, or thing.
-
E.
neighborhoodCharacteristic
Indicates that a particular characteristic, feature, or quality is associated with or describes a given neighborhood.
- 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d3aa84a9ac819093d551005a1c8f3d |
completed | April 6, 2026, 12:43 p.m. |
| PD | Predicate disambiguation | batch_69d3955f61f88190b8d37ff645cd44d3 |
completed | April 6, 2026, 11:13 a.m. |
Created at: April 6, 2026, 11:11 a.m.