Triple
T20006901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DCI Banks |
E494482
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Caroline Catz |
—
|
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: Caroline Catz | Statement: [DCI Banks, stars, Caroline Catz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caroline Catz Context triple: [DCI Banks, stars, Caroline Catz]
-
A.
Caroline Catz
chosen
Caroline Catz is an English actress best known for her roles in television dramas such as "Doc Martin" and "DCI Banks."
-
B.
Caroline Heubel
Caroline Heubel was the mother of Jenny von Westphalen, who later became the wife of philosopher and economist Karl Marx.
-
C.
Caroline Hirsch
Caroline Hirsch is an American businesswoman and influential comedy impresario best known as the founder and owner of the iconic New York City comedy club Carolines on Broadway.
-
D.
Caroline Benjo
Caroline Benjo is a French film producer known for her work on acclaimed European art-house and independent films.
-
E.
Caroline Michels
Caroline Michels is an individual notable for bearing the surname Michels, though specific widely recognized biographical details about her are not well documented.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a648a88190853ee741edcf6ca2 |
completed | April 20, 2026, 5:25 p.m. |
Created at: April 11, 2026, 3:33 p.m.