Triple
T36937366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kino der Toten |
E913654
|
entity |
| Predicate | startingCharacters |
P82030
|
FINISHED |
| Object | Tank Dempsey |
—
|
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: Tank Dempsey | Statement: [Kino der Toten, startingCharacters, Tank Dempsey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingCharacters Context triple: [Kino der Toten, startingCharacters, Tank Dempsey]
-
A.
openingMovementCharacter
Indicates the characteristic or quality that defines how the opening movement of a work is expressed or perceived.
-
B.
openingCharacter
Indicates that one entity is the first character or symbol at the beginning of another entity (such as a string, word, or text).
-
C.
characterSelection
chosen
Indicates the relationship where a user or system chooses one or more characters from a set of available options.
-
D.
challengesCharacters
Indicates that one entity presents difficulties, obstacles, or opposition to another entity, testing its abilities or resolve.
-
E.
characterAcquisition
Indicates the relationship in which an entity comes to possess, gain, or obtain a character, trait, or attribute.
- 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_69f76e8a6a5c81909c1febf32bf3fe23 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00bb3a6f888190b3ecd0fbc9af9b4a |
completed | May 10, 2026, 5:07 p.m. |
| PD | Predicate disambiguation | batch_6a00b902dbf881909e098ff102b7ea7e |
completed | May 10, 2026, 4:57 p.m. |
Created at: May 3, 2026, 4:13 p.m.