Triple
T19462106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Eros |
E486897
|
entity |
| Predicate | accessFrom |
P1985
|
FINISHED |
| Object | Kamini |
—
|
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: Kamini | Statement: [Mount Eros, accessFrom, Kamini]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kamini Context triple: [Mount Eros, accessFrom, Kamini]
-
A.
Kamini
chosen
Kamini is a small coastal village and harbor on the Greek island of Hydra, known for its traditional stone houses and picturesque waterfront.
-
B.
Kamini
Kamini is the mysterious on-screen singer character, portrayed by Madhubala, who lip-syncs to the iconic Hindi film song "Aayega Aanewala" in the classic movie Mahal.
-
C.
Kamshet
Kamshet is a scenic hill-station and paragliding destination in Maharashtra’s Western Ghats, known for its lakes, forts, and rural landscapes.
-
D.
Ahilawati
Ahilawati is a character from Javanese and Indonesian wayang (shadow puppet) epics, known primarily as the wife of the heroic warrior Gatotkaca.
-
E.
Chitrari
Chitrari is an alternative name for the Khowar language, an Indo-Aryan language spoken primarily in the Chitral region of northern Pakistan.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633cd6c148190933b4d6bfe84cbe1 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:38 p.m.