Triple
T13243103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Resh Lakish |
E315328
|
entity |
| Predicate | biographicalTheme |
P75959
|
FINISHED |
| Object | repentant sinner |
—
|
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: repentant sinner | Statement: [Resh Lakish, biographicalTheme, repentant sinner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: biographicalTheme Context triple: [Resh Lakish, biographicalTheme, repentant sinner]
-
A.
hasBiographicalTheme
chosen
Indicates that something (such as a work, text, or content) centers on or significantly involves biographical subject matter, such as a person’s life, experiences, or personal history.
-
B.
hasBiographicalStyle
Indicates that something is characterized by or presented in a biographical manner or style.
-
C.
genreOfBiographicalTradition
Indicates that one entity is the genre classification associated with a particular biographical tradition of another entity.
-
D.
includesBiographiesOf
Indicates that one entity contains or features biographical information about another entity.
-
E.
usesBiographicalStructure
Indicates that one entity employs or is organized according to the biographical structure of another entity (e.g., a work structured around a person’s life story).
- 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d59e84c8190a9e547d0fe26a5f9 |
completed | April 10, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69d98bcb21648190aef241de1e7887e2 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:23 p.m.