Triple
T37982430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patti Levin |
E947589
|
entity |
| Predicate | roleWithLaurieGarvey |
P38683
|
FINISHED |
| Object | recruits Laurie Garvey into the Guilty Remnant |
—
|
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: recruits Laurie Garvey into the Guilty Remnant | Statement: [Patti Levin, roleWithLaurieGarvey, recruits Laurie Garvey into the Guilty Remnant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleWithLaurieGarvey Context triple: [Patti Levin, roleWithLaurieGarvey, recruits Laurie Garvey into the Guilty Remnant]
-
A.
relationshipToLaurie
chosen
Indicates the specific type of relationship or connection that an entity has to Laurie.
-
B.
roleOfCathy Hughes
Indicates the specific position, function, or capacity that Cathy Hughes holds or performs in relation to another entity or context.
-
C.
roleOfDanLauria
Indicates that Dan Lauria holds or performs a particular role or character in a work or context.
-
D.
roleOfJennifer Morris
Indicates that Jennifer Morris holds or performs a particular role, position, or function in relation to another entity or context.
-
E.
roleOfCarmen Pavlovic
Indicates that the specified role or position is held or performed by Carmen Pavlovic.
- 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_69f76ef8a1d08190a741bbbc5970e3b3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.