Triple
T35997745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arch of Triumph (1939 film) |
E1041039
|
entity |
| Predicate | hasWorkAuthorOfSource |
P71864
|
FINISHED |
| Object | Erich Maria Remarque |
—
|
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: Erich Maria Remarque | Statement: [Arch of Triumph (1939 film), hasWorkAuthorOfSource, Erich Maria Remarque]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkAuthorOfSource Context triple: [Arch of Triumph (1939 film), hasWorkAuthorOfSource, Erich Maria Remarque]
-
A.
hasSourceWork
Indicates that something originates from, is derived from, or is based on a particular source work.
-
B.
hasSourceWorkCreators
Indicates that a work is associated with the creators of its original source work from which it is derived or adapted.
-
C.
hasAuthorOfWorkSetThere
Indicates that the location is a setting in a work created by the specified author.
-
D.
hasAuthorOfSourceMaterial
chosen
Indicates that one entity is the creator or writer of the original source material on which another entity is based.
-
E.
anonymousAuthorOfSourceWork
Indicates that a person is the (unidentified or unnamed) author of a given source 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_69f76e29084c819083987b828d414de7 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fe9dfaa2d08190b2084f63f842eb6b |
completed | May 9, 2026, 2:37 a.m. |
| PD | Predicate disambiguation | batch_69fe9bba947c81908b0b2b92a4d19b37 |
completed | May 9, 2026, 2:28 a.m. |
Created at: May 3, 2026, 4:07 p.m.