Triple
T19001117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bed of Rose’s |
E464952
|
entity |
| Predicate | characterRoleOfRose |
P23263
|
FINISHED |
| Object | prostitute |
—
|
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: prostitute | Statement: [Bed of Rose’s, characterRoleOfRose, prostitute]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterRoleOfRose Context triple: [Bed of Rose’s, characterRoleOfRose, prostitute]
-
A.
featuresCharacterRole
chosen
Indicates that a work includes a character appearing in a specific narrative or functional role.
-
B.
characterRoleOfGriffin
Indicates that an entity has the character role of a griffin within a given context, such as a story, game, or artwork.
-
C.
characterInWorkDescribedAs
Indicates that a character is portrayed or described in a particular way within a specific work.
-
D.
roleInRomeoAndJuliet
Indicates the specific character or part that an entity plays in the work "Romeo and Juliet."
-
E.
relationshipCharacterizedAs
Indicates that one relationship is described, defined, or typified in terms of another specified characteristic or relational type.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6863cf4819096e471d19f9a714c |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.