Triple
T34109399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aabenraa Bay |
E874797
|
entity |
| Predicate | hasPrimarySettlementOnShore |
P969
|
FINISHED |
| Object | Aabenraa |
E249394
|
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: Aabenraa | Statement: [Aabenraa Bay, hasPrimarySettlementOnShore, Aabenraa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimarySettlementOnShore Context triple: [Aabenraa Bay, hasPrimarySettlementOnShore, Aabenraa]
-
A.
hasCityOnShore
chosen
Indicates that a city is located on or directly adjacent to the shore of a body of water.
-
B.
primaryIslandOnShore
Indicates that one island is the main or most significant island located along a particular shore or coastline.
-
C.
hasShoreOn
Indicates that one geographic entity borders or is directly adjacent to the shore of another body of water.
-
D.
hasPrimaryLanguageOfNearbyShore
Indicates that an entity uses as its primary language the language predominantly spoken along the nearby shore or coastal area.
-
E.
hasShoreNear
Indicates that one entity is located close enough to another entity’s shore or coastline to be considered nearby.
- F. None of above.
Provenance (4 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_69f349a80d4481908527317d43f5c579 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a023f290e3081909a465d6cfb79518a |
completed | May 11, 2026, 8:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a59fff23ab4819086a927e83730b621 |
completed | July 17, 2026, 10:12 a.m. |
| PD | Predicate disambiguation | batch_6a0238d1436c8190ab0251030b01902e |
completed | May 11, 2026, 8:15 p.m. |
Created at: May 1, 2026, 1:53 a.m.