Triple
T23540765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erik King |
E577738
|
entity |
| Predicate | hasActedIn |
P15620
|
FINISHED |
| Object | Ice Princess |
—
|
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: Ice Princess | Statement: [Erik King, hasActedIn, Ice Princess]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ice Princess Context triple: [Erik King, hasActedIn, Ice Princess]
-
A.
Ice Princess
chosen
Ice Princess is a 2005 Disney teen sports drama film about a physics-obsessed high school girl who pursues her dream of becoming a competitive figure skater.
-
B.
Ice Princess
Ice Princess is a fictional character from the fantasy world of Planet Drool in the family adventure film "The Adventures of Sharkboy and Lavagirl."
-
C.
Ice Kingdom
The Ice Kingdom is a frozen, mountainous realm ruled by the Ice King in the post-apocalyptic fantasy world of Adventure Time’s Land of Ooo.
-
D.
Snow Queen
"Snow Queen" is a song featured on the album *City of Gold*, likely characterized by wintry, mystical themes suggested by its title.
-
E.
Snow Queen
"Snow Queen" is a lesser-known 1976 pop song by Elton John and Kiki Dee, released as the B-side to their hit duet "Don't Go Breaking My Heart."
- 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_69e245f9d5d08190a4a20004e1784e20 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1ae1b3a8c8190b5b6a58f0476c5d2 |
completed | April 29, 2026, 7:07 a.m. |
Created at: April 17, 2026, 6:10 p.m.