Triple
T32843521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ship in a Bottle |
E840034
|
entity |
| Predicate | featuresHolodeckCharacter |
P93957
|
FINISHED |
| Object | Countess Regina Bartholomew |
—
|
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: Countess Regina Bartholomew | Statement: [Ship in a Bottle, featuresHolodeckCharacter, Countess Regina Bartholomew]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresHolodeckCharacter Context triple: [Ship in a Bottle, featuresHolodeckCharacter, Countess Regina Bartholomew]
-
A.
featuresCharacterWith
chosen
Indicates that one entity (such as a work or product) includes or presents a particular character as part of its content.
-
B.
AICharacteristics
Indicates the defining traits, behaviors, or properties that characterize an artificial intelligence system.
-
C.
featuresReturningCharacterFrom
Indicates that a work includes the reappearance of a character who previously appeared in the referenced source work.
-
D.
featuresFictionalElement
Indicates that one entity includes, presents, or incorporates a fictional element (such as an imaginary character, place, object, or concept) as part of its content or composition.
-
E.
featuresFictionalProgram
Indicates that a work includes or presents a fictional program (such as a TV show, software, or in-universe broadcast) as part of its content.
- 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_69f3493ff0888190b51e974eae2a7834 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a013f09b0988190ba3179c7d56c726a |
completed | May 11, 2026, 2:29 a.m. |
| PD | Predicate disambiguation | batch_6a013e600e248190a1a9c363702c8586 |
completed | May 11, 2026, 2:26 a.m. |
Created at: May 1, 2026, 1:16 a.m.