Triple
T14307611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harrenhal |
E354736
|
entity |
| Predicate | TVPortrayalLocation |
P113256
|
FINISHED |
| Object | Game of Thrones television adaptation |
—
|
LITERAL 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: Game of Thrones television adaptation | Statement: [Harrenhal, TVPortrayalLocation, Game of Thrones television adaptation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: TVPortrayalLocation Context triple: [Harrenhal, TVPortrayalLocation, Game of Thrones television adaptation]
-
A.
plotLocation
Indicates the relationship between a creative work and the place or setting where its story or events occur.
-
B.
workLocationOfFictionalCharacter
Indicates the place or organization where a fictional character is depicted as working within their narrative context.
-
C.
fictionalTryoutLocationInSeries
Indicates the location where a fictional tryout event takes place within a specific series.
-
D.
formerFilmingLocation
Indicates that a place was once used as a filming location for a work but is no longer used for that purpose.
-
E.
portrayedByRealWorldLocation
chosen
Indicates that a fictional or represented location is depicted or substituted by an actual real-world location.
- 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_69d8278ed42c8190b9f882dcce611347 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de85b156b0819083f2bd319deed1b6 |
completed | April 14, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69de2a8f81f08190af737e1654847aa6 |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:12 a.m.