Triple
T29825170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Finished Mystery |
E757357
|
entity |
| Predicate | basisOnEarlierWorkOf |
P69688
|
FINISHED |
| Object | Charles Taze Russell |
—
|
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: Charles Taze Russell | Statement: [The Finished Mystery, basisOnEarlierWorkOf, Charles Taze Russell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basisOnEarlierWorkOf Context triple: [The Finished Mystery, basisOnEarlierWorkOf, Charles Taze Russell]
-
A.
basedOnOwnWork
Indicates that something is derived from, created using, or directly built upon the subject’s own prior work.
-
B.
basedOnWorkAppearedIn
Indicates that something is derived from, adapted from, or otherwise created using a work that appeared in a specified source or publication.
-
C.
basedOnEarlierCollaboration
Indicates that the relationship or action arises from, or is grounded in, a prior collaboration between the involved entities.
-
D.
buildsUponWorkOf
chosen
Indicates that one entity is created, developed, or derived by using, extending, or incorporating the work produced by another entity.
-
E.
hasWorkBasedOn
Indicates that one work is derived from, adapted from, or otherwise based on the content of another work.
- 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_69f22457c84c8190a6d9f56bc74082a9 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67597ec4081909c0b453a69f14c28 |
completed | May 2, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 29, 2026, 5:31 p.m.