Triple
T28207915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horror of Dracula |
E717080
|
entity |
| Predicate | alternateTitleUS |
P110584
|
FINISHED |
| Object | Horror of Dracula |
—
|
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: Horror of Dracula | Statement: [Horror of Dracula, alternateTitleUS, Horror of Dracula]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alternateTitleUS Context triple: [Horror of Dracula, alternateTitleUS, Horror of Dracula]
-
A.
hasAlternateTitleRegion
chosen
Indicates that an entity has an alternate title that is specifically used or valid within a particular geographic region.
-
B.
originalTitleInUnitedStates
Indicates the title originally used for a work specifically in the United States.
-
C.
alternateTitleOfAdaptedEdition
Indicates that a title is an alternative title specifically for an adapted edition of a work, rather than for the original version.
-
D.
haveAlternativeTitle
Indicates that an entity is known by one or more alternative titles or names in addition to its primary title.
-
E.
alternateInterpretationOfTitle
Indicates that one title is an alternative interpretation or reading of another title, reflecting a different way the original title can be understood.
- 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_69efd6b826908190857e6e7dad74ed93 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 27, 2026, 10:36 p.m.