Triple
T23074331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexandra Elizabeth Kingston |
E575285
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Cracker |
—
|
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: Cracker | Statement: [Alexandra Elizabeth Kingston, notableWork, Cracker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cracker Context triple: [Alexandra Elizabeth Kingston, notableWork, Cracker]
-
A.
Cracker
chosen
Cracker is a British crime drama television series centered on a brilliant but troubled criminal psychologist who helps the police solve complex cases.
-
B.
Primus
Primus is an American rock band known for its eccentric, genre-blending sound and the virtuosic bass playing of frontman Les Claypool.
-
C.
Primus
The Primus is the presiding bishop and senior cleric of the Scottish Episcopal Church, serving as its spiritual leader and representative.
-
D.
Primus
Primus is a godlike creator deity in the Transformers universe, known as the benevolent counterpart and eternal enemy of the chaos-bringer Unicron.
-
E.
Primus
Primus is a real-time framework that provides a unified interface over various WebSocket and fallback transports to simplify building scalable, event-driven applications.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245be28d48190ad1348d5a73db37d |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18c61bb7c8190a3d9b1fba173cdff |
completed | April 29, 2026, 4:43 a.m. |
Created at: April 17, 2026, 3:56 p.m.