Triple
T25383896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bobby Dagen |
E631466
|
entity |
| Predicate | bookTitleInUniverse |
P113153
|
FINISHED |
| Object | S.U.R.V.I.V.E. |
—
|
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: S.U.R.V.I.V.E. | Statement: [Bobby Dagen, bookTitleInUniverse, S.U.R.V.I.V.E.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bookTitleInUniverse Context triple: [Bobby Dagen, bookTitleInUniverse, S.U.R.V.I.V.E.]
-
A.
bookPublicationInUniverse
Indicates that a book is published or exists within a specific fictional or narrative universe.
-
B.
titleOfBook
Indicates that one entity is the title assigned to a particular book.
-
C.
inUniverseTitle
chosen
Indicates that a work’s title is the one used within the fictional universe itself, as opposed to an external or real-world title.
-
D.
fictionalWorkTitle
Indicates the title assigned to a fictional work, such as a novel, film, or game.
-
E.
bookTieIn
Indicates that one creative work is directly related to another as a tie-in, typically produced to promote, expand, or accompany the original work (such as a book based on a film, game, or TV series).
- 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_69e75a8c50788190aabaa9f96710fc43 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f56566c5408190a8841d2c45dcf52c |
completed | May 2, 2026, 2:45 a.m. |
| PD | Predicate disambiguation | batch_69f45d0dbc8c8190beecce679fce90a4 |
completed | May 1, 2026, 7:58 a.m. |
Created at: April 21, 2026, 1:46 p.m.