Triple
T21565367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Underground Man |
E532148
|
entity |
| Predicate | relationshipToLiza |
P144260
|
FINISHED |
| Object | emotionally abusive |
—
|
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: emotionally abusive | Statement: [Underground Man, relationshipToLiza, emotionally abusive]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToLiza Context triple: [Underground Man, relationshipToLiza, emotionally abusive]
-
A.
relationshipToLaurie
Indicates the specific type of relationship or connection that an entity has to Laurie.
-
B.
relationshipTypeWithLizzieEustace
Indicates the specific nature or category of relationship that an entity has with Lizzie Eustace.
-
C.
relationshipToAllison
Indicates the specific type of personal, familial, or social relationship that an entity has with Allison.
-
D.
relationshipToMary
Indicates that one entity stands in a specified personal or social relationship to Mary.
-
E.
relationshipToVanessa
Indicates the specific type of personal or social relationship that an entity has with Vanessa.
- 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_69e0c460db088190828c64206a450273 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eed2e777c881908de84493fa939ff3 |
completed | April 27, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69e6320c8c2c81908bf031447d66a052 |
completed | April 20, 2026, 2:02 p.m. |
| PDg | Predicate description generation | batch_69e633bf34c481909925d8dc1a633a65 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 16, 2026, 6:30 p.m.