Triple
T31087532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cynthia Malkin |
E792284
|
entity |
| Predicate | spouseRepresents |
P192715
|
FINISHED |
| Object | Connecticut |
—
|
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: Connecticut | Statement: [Cynthia Malkin, spouseRepresents, Connecticut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseRepresents Context triple: [Cynthia Malkin, spouseRepresents, Connecticut]
-
A.
spouse represented
Indicates that one person legally or formally acted on behalf of their spouse, such as in a professional, legal, or official capacity.
-
B.
spouseRepresented
Indicates that one person served as the legal or official representative (e.g., agent, attorney, or proxy) of their spouse in some formal capacity or proceeding.
-
C.
spouseMember
Indicates that one entity is the spouse (married partner) of another entity.
-
D.
spouse
Indicates that two entities are married to each other in a legally or socially recognized partnership.
-
E.
spouseInFamily
Indicates that a person is a spouse (married partner) within the context of a specific family unit.
- 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_69f224ce48348190bd0fc23f656ed683 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
| PDg | Predicate description generation | batch_69fd28379d2c8190903ba228ee1cc756 |
completed | May 8, 2026, 12:03 a.m. |
Created at: April 29, 2026, 9:02 p.m.