Triple
T7385556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Coupée |
E170370
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Sark |
E29748
|
NE 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: Sark | Statement: [La Coupée, connects, Sark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sark Context triple: [La Coupée, connects, Sark]
-
A.
Sark
chosen
Sark is a small, car-free island in the English Channel known for its rugged coastline, traditional feudal-style governance history, and designation as a Dark Sky Island.
-
B.
Sar
Sar is the family name of Pol Pot, the Cambodian revolutionary leader and dictator who headed the Khmer Rouge regime responsible for the Cambodian genocide.
-
C.
Sinarka
Sinarka is an active stratovolcano located on Shiashkotan Island in the central Kuril Islands chain of Russia.
-
D.
Sarju
Sarju is an alternate name for the Sarayu, a river historically associated with the ancient Indian city of Ayodhya and revered in Hindu tradition.
-
E.
Sarmast
Sarmast is an honorific title associated with the renowned Sindhi Sufi poet and mystic Sachal Sarmast.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c68a5d0ed08190b6d361e68f813330 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1f117ec8190a97cbd0b35d5811a |
completed | March 27, 2026, 9:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8b4e3181481909eec1a09ae295923 |
completed | March 29, 2026, 5:13 a.m. |
Created at: March 27, 2026, 3:08 p.m.