Triple
T20997102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ingmar Bergman |
E517177
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Gun Grut |
—
|
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: Gun Grut | Statement: [Ingmar Bergman, spouse, Gun Grut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gun Grut Context triple: [Ingmar Bergman, spouse, Gun Grut]
-
A.
Gun Grut
chosen
Gun Grut was a Swedish journalist and writer best known for being married to renowned film director Ingmar Bergman.
-
B.
Grohg
Grohg is an early ballet score by American composer Aaron Copland that explores macabre, expressionist themes and later provided material for his Dance Symphony.
-
C.
Throsk
Throsk is a small village in central Scotland situated on the River Forth within the Stirling council area.
-
D.
Gurgi
Gurgi is a timid yet loyal, creature-like companion character from Disney’s animated fantasy film "The Black Cauldron."
-
E.
Zorak
Zorak is a villainous, mantis-like alien and sarcastic bandleader best known as a recurring character on the animated talk show parody "Space Ghost Coast to Coast."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b5006e2881909fc2383f841740cc |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc21838081909872eed21bc12a08 |
completed | April 21, 2026, 4:25 a.m. |
Created at: April 16, 2026, 1:51 p.m.