Triple
T22105651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adventfjorden |
E546277
|
entity |
| Predicate | hasNearbyCoalMiningHistory |
P89210
|
FINISHED |
| Object | Longyearbyen coal mining |
—
|
LITERAL 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: Longyearbyen coal mining | Statement: [Adventfjorden, hasNearbyCoalMiningHistory, Longyearbyen coal mining]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyCoalMiningHistory Context triple: [Adventfjorden, hasNearbyCoalMiningHistory, Longyearbyen coal mining]
-
A.
hasCoalMiningHistory
Indicates that an entity has a past or ongoing involvement in coal mining activities or industry.
-
B.
hasNearbyFormerMiningCommunity
chosen
Indicates that an entity is located close to a community that previously hosted mining activities but is no longer an active mining site.
-
C.
hasCoalMineNearby
Indicates that a location or entity is situated close to at least one coal mine.
-
D.
hasCoalMiningCompany
Indicates that an entity is associated with or owns a company whose primary business is coal mining.
-
E.
locatedInFormerMiningArea
Indicates that an entity is situated within an area that was previously used for mining activities.
- F. None of above.
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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12918d7a4819080283c287a253c9f |
completed | April 28, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69e71b2ed7348190b6fa2e52f54393fb |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:30 p.m.