Triple
T3486861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Churchill |
E73626
|
entity |
| Predicate | isPrimeLocationFor |
P7849
|
FINISHED |
| Object | Northern Lights observation |
—
|
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: Northern Lights observation | Statement: [Churchill, isPrimeLocationFor, Northern Lights observation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPrimeLocationFor Context triple: [Churchill, isPrimeLocationFor, Northern Lights observation]
-
A.
isPointWhere
Indicates that one entity is the specific location or point at which another entity, event, or condition occurs or is defined.
-
B.
isNamedLocation
Indicates that an entity is a specific, identifiable place referred to by a proper name.
-
C.
possibleLocation
Indicates that an entity may be located at, or could plausibly occur in, a specified place or spatial context.
-
D.
isSiteOf
chosen
Indicates that a location or place serves as the setting or host for a particular event, activity, or feature.
-
E.
isLocatedInSettlement
Indicates that an entity is situated within or belongs to a specific human settlement, such as a town, village, or city.
- 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_69ad85cca8d4819088494e9f3340fab5 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbb9059f881908f9cbe544365c8df |
completed | March 8, 2026, 6:10 p.m. |
| PD | Predicate disambiguation | batch_69adae0935ac8190bfa8a8bd3dcd3301 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.