Triple
T22725003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Costa Rican Summer |
E561965
|
entity |
| Predicate | fictionalOrNonfictional |
P14491
|
FINISHED |
| Object | fictional work |
—
|
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: fictional work | Statement: [Costa Rican Summer, fictionalOrNonfictional, fictional work]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fictionalOrNonfictional Context triple: [Costa Rican Summer, fictionalOrNonfictional, fictional work]
-
A.
isNonfiction
Indicates that the work or content is factual rather than fictional, based on real events, people, or information.
-
B.
fictionalGenre
Indicates that a work of fiction belongs to or is categorized under a particular narrative genre or style.
-
C.
fictionalStatus
chosen
Indicates that an entity exists only in imagination or narrative and does not correspond to a real-world counterpart.
-
D.
fictionalMaterial
Indicates that something is made of, composed of, or incorporates a material that exists only in fiction or imagination.
-
E.
fictionalFocus
Indicates that the primary emphasis or attention within a context is placed on fictional content, elements, or aspects.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17928a21c8190a1b888754ba7808b |
completed | April 29, 2026, 3:21 a.m. |
| PD | Predicate disambiguation | batch_69eed2a971c0819088af574e40c9343f |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:20 p.m.