Triple
T21467313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Book of Laughter and Forgetting |
E529624
|
entity |
| Predicate | notableCharacter |
P1481
|
FINISHED |
| Object | Marketa |
—
|
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: Marketa | Statement: [The Book of Laughter and Forgetting, notableCharacter, Marketa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marketa Context triple: [The Book of Laughter and Forgetting, notableCharacter, Marketa]
-
A.
Markéta
chosen
Markéta is a common Czech female given name, equivalent to Margaret in English.
-
B.
Marga
Marga is a feminine given name, commonly used as a short or diminutive form of names like Margarita or Margareta.
-
C.
Arleta
Arleta is a residential neighborhood in the San Fernando Valley region of Los Angeles, California.
-
D.
Haná
Haná is a historical ethnographic region in central Moravia in the Czech Republic, known for its fertile agricultural land, distinctive folk traditions, and Hanakian dialect.
-
E.
Turnesa
Turnesa is the surname of a prominent American golfing family that produced several notable professional golfers in the early to mid-20th century.
- 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_69e0c459acb481909bb6ee452a0045c7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9f415d48190a2b0993a4f3c018f |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:14 p.m.