Triple
T24642462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Cozner |
E610007
|
entity |
| Predicate | spouseDivision |
P156882
|
FINISHED |
| Object | 99th Precinct |
—
|
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: 99th Precinct | Statement: [Kevin Cozner, spouseDivision, 99th Precinct]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseDivision Context triple: [Kevin Cozner, spouseDivision, 99th Precinct]
-
A.
spouse
Indicates that two entities are married to each other in a legally or socially recognized partnership.
-
B.
throughSpouse
Indicates a relationship or connection that exists indirectly between two entities by way of one entity’s spouse.
-
C.
spouseType
Indicates the specific role or category of a person within a spousal relationship (e.g., husband, wife, partner).
-
D.
partnerInDivorce
Indicates that two individuals are parties on opposing sides in the same divorce proceeding.
-
E.
spouseMember
Indicates that one entity is the spouse (married partner) of another entity.
- 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_69e2c4d28f848190ac38c400060e943d |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f40db2b5e08190bb55d02a4ceba306 |
completed | May 1, 2026, 2:19 a.m. |
| PD | Predicate disambiguation | batch_69f2a6d2b20881908dcc3b15cbe3e5b0 |
completed | April 30, 2026, 12:48 a.m. |
| PDg | Predicate description generation | batch_69f40b2f49688190aa1217b7a456dd63 |
completed | May 1, 2026, 2:08 a.m. |
Created at: April 18, 2026, 2:33 a.m.