Triple
T6899050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig Ferguson |
E159445
|
entity |
| Predicate | performedVoiceRoleIn |
P43874
|
FINISHED |
| Object | How to Train Your Dragon |
E268290
|
NE FINISHED |
How this triple was built (3 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: How to Train Your Dragon | Statement: [Craig Ferguson, performedVoiceRoleIn, How to Train Your Dragon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: How to Train Your Dragon Context triple: [Craig Ferguson, performedVoiceRoleIn, How to Train Your Dragon]
-
A.
How to Train Your Dragon (film series)
chosen
How to Train Your Dragon (film series) is a popular animated fantasy franchise from DreamWorks Animation that follows a young Viking named Hiccup and his dragon Toothless through adventures that explore friendship, courage, and the coexistence of humans and dragons.
-
B.
How to Train Your Dragon land
How to Train Your Dragon land is a themed area in Universal’s Epic Universe park that immerses guests in the Viking village and dragon-filled world inspired by the How to Train Your Dragon films.
-
C.
Dragons
Dragons is a professional Welsh rugby union team based in Newport that competes in major regional and international club competitions.
-
D.
Dragons
Dragons is the common short name for the St George Illawarra Dragons, a professional rugby league club based in New South Wales, Australia, that competes in the National Rugby League (NRL).
-
E.
Dragons
Dragons is the common short name for the Chunichi Dragons, a professional baseball team based in Nagoya, Japan, that competes in Nippon Professional Baseball’s Central League.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedVoiceRoleIn Context triple: [Craig Ferguson, performedVoiceRoleIn, How to Train Your Dragon]
-
A.
voiceActingRoleIn
chosen
Indicates that an entity performs a voice acting role in a specified work or production.
-
B.
voiceActingRole
Indicates that one entity performs the voice acting for a character or role in a work associated with the other entity.
-
C.
playedRoleIn
Indicates that an entity performed or assumed a specific role or character within a particular event, production, or context.
-
D.
hasFictionalRole
Indicates that an entity plays or is assigned a specific role within a fictional work or narrative.
-
E.
playsInRole
Indicates that an entity performs or appears in a specific role within a production, event, or context.
- F. None of above.
Provenance (4 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_69c6883822e0819091e321526f20ae0a |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d95d67448190857f36b8115b03f6 |
completed | March 27, 2026, 7:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c748eb23888190bca6e42dc03ab31b |
completed | March 28, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69c6d7b7681481909ec50509b19fcf81 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:24 p.m.