Triple
T10649487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Yates |
E250923
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Krull |
E877217
|
NE 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: Krull | Statement: [Peter Yates, directed, Krull]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Krull Context triple: [Peter Yates, directed, Krull]
-
A.
Krull
chosen
Krull is a 1983 science fantasy film blending sword-and-sorcery adventure with space opera elements, directed by Peter Yates.
-
B.
Gjallarhorn
Gjallarhorn is the resounding horn of the god Heimdall in Norse mythology, famously used to signal the onset of Ragnarök.
-
C.
Krammer
Krammer is a body of water in the Rhine–Meuse–Scheldt delta in the southwestern Netherlands, known as a former estuarine channel now separated from the sea by dams and used for recreation and water management.
-
D.
Blixem
Blixem is an alternative name for Blitzen, one of Santa Claus’s traditional flying reindeer known from the Christmas poem “A Visit from St. Nicholas.”
-
E.
Hellmut
Hellmut is a masculine given name of German origin, used as a variant spelling of Helmut.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6dfe3ea08819094a945ebb7fc4d3a |
completed | April 8, 2026, 11:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d988530f288190b8150d159f723a74 |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 8, 2026, 9:06 p.m.