Triple
T15428046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gjöll bridge |
E369563
|
entity |
| Predicate | crosses |
P416
|
FINISHED |
| Object | river Gjöll |
E1147873
|
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: river Gjöll | Statement: [Gjöll bridge, crosses, river Gjöll]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: river Gjöll Context triple: [Gjöll bridge, crosses, river Gjöll]
-
A.
river Gjöll
chosen
The river Gjöll is a mythological river in Norse cosmology that separates the realm of the living from Helheim, the land of the dead.
-
B.
Fyris River
The Fyris River is a notable waterway in eastern Sweden that flows through the city of Uppsala and is closely associated with its history and landscape.
-
C.
River Trym
The River Trym is a small river in Bristol, England, that flows through the northern suburbs before joining the River Avon.
-
D.
River Balder
River Balder is a small river in County Durham, England, that flows through Baldersdale before joining the River Tees.
-
E.
Oreälven
Oreälven is a river in central Sweden that flows through Dalarna County and ultimately drains into Lake Siljan.
- 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_69d85a1849f48190bf898068b2806fae |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03ec31f4881908b26ff7c381d7bc9 |
completed | April 16, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1a8099448190be71f7b649c7e545 |
completed | May 9, 2026, 11:29 a.m. |
Created at: April 10, 2026, 3:20 a.m.