Triple
T10296660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inverness-shire |
E241507
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Rùm |
E72820
|
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: Rùm | Statement: [Inverness-shire, contains, Rùm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rùm Context triple: [Inverness-shire, contains, Rùm]
-
A.
Rùm
chosen
Rùm is a small, rugged island in Scotland’s Inner Hebrides, known for its dramatic mountainous landscape, wildlife, and status as a National Nature Reserve.
-
B.
Rufaa
Rufaa is a town in Sudan located in Al Jazirah state, known primarily as an agricultural and trading center along the Blue Nile.
-
C.
Rukuhia
Rukuhia is a rural locality in the Waikato region of New Zealand, situated just south of Hamilton and known for its proximity to Hamilton Airport.
-
D.
Ratoma
Ratoma is a major urban district of Conakry, the capital city of Guinea.
-
E.
Tannat
Tannat is a robust, tannin-rich red wine grape variety traditionally associated with southwestern France and now also widely grown in Uruguay and other New World regions.
- 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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2ebd258819099fadddcd13099fc |
completed | April 7, 2026, 9:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71d2cc9c48190bc36f6a4f8144b7f |
completed | April 9, 2026, 3:29 a.m. |
Created at: April 6, 2026, 11:43 a.m.