Triple
T11430662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kiss the Girl |
E270869
|
entity |
| Predicate | narrativeLocationInWork |
P45019
|
FINISHED |
| Object | boat scene on the lagoon |
—
|
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: boat scene on the lagoon | Statement: [Kiss the Girl, narrativeLocationInWork, boat scene on the lagoon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: narrativeLocationInWork Context triple: [Kiss the Girl, narrativeLocationInWork, boat scene on the lagoon]
-
A.
locationOfNarrative
Indicates the place or setting where the events or story described in the narrative occur.
-
B.
narrativeLocationType
Indicates the type or role of a location within the structure or context of a narrative (e.g., setting, origin, destination).
-
C.
narrativeSettingOfWork
chosen
Indicates that a particular place, time, or context serves as the narrative setting in which a work’s story or events occur.
-
D.
locationWithinFiction
Indicates that one fictional location is situated inside or contained within another fictional location.
-
E.
locationOfPassage
Indicates the place or area through which a passage, route, or transit occurs or is situated.
- 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_69d6aadeef688190874bcecd88b3dd9b |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d806c1bfb881909720c74fe0fa837f |
completed | April 9, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69d7e71436f88190ac7e45a04ea5c987 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:35 p.m.