Triple
T23504115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Split |
E572234
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Marjan Hill |
—
|
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: Marjan Hill | Statement: [Split, hasLandmark, Marjan Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marjan Hill Context triple: [Split, hasLandmark, Marjan Hill]
-
A.
Marjan Hill
chosen
Marjan Hill is a forested hill and popular recreational area overlooking the city of Split on Croatia’s Adriatic coast, known for its scenic viewpoints, walking trails, and historic sites.
-
B.
Elizabeth Arlen
Elizabeth Arlen is an actress best known for her role in the 1990 supernatural horror-thriller film "The First Power."
-
C.
Melissa Merwin
Melissa Merwin is the wife of American actor Joshua Malina.
-
D.
Jo Shapcott
Jo Shapcott is a contemporary British poet known for her inventive, often surreal verse and multiple major awards, including the Costa Poetry Award.
-
E.
Karen Hood
Karen Hood is the central protagonist of the film "Welcome to L.A.," around whom the story’s interpersonal dramas and emotional developments revolve.
- 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a8fedbec8190b183661edaba4cd4 |
completed | April 29, 2026, 6:45 a.m. |
Created at: April 17, 2026, 6:06 p.m.