Triple
T15040604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mariaberget |
E378588
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Zinkensdamm |
E378590
|
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: Zinkensdamm | Statement: [Mariaberget, locatedNear, Zinkensdamm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zinkensdamm Context triple: [Mariaberget, locatedNear, Zinkensdamm]
-
A.
Zinkensdamm
chosen
Zinkensdamm is a residential and recreational area in Stockholm known for its sports grounds, park spaces, and location on the island district of Södermalm.
-
B.
Hohenwarte Dam
Hohenwarte Dam is a large hydroelectric and flood-control dam on the Saale River in Thuringia, Germany, forming one of the country’s significant reservoir lakes.
-
C.
Schwelm Dam
Schwelm Dam is a German reservoir dam that was one of the targets attacked during the World War II Dambusters Raid.
-
D.
Diemel Dam
Diemel Dam is a German reservoir dam that was one of the targets attacked during the World War II Dambusters Raid.
-
E.
Ballindamm
Ballindamm is a prominent boulevard in central Hamburg, Germany, known for its upscale shops, offices, and views over the Binnenalster lake.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded82e79a481908ddb9609af8c4407 |
completed | April 15, 2026, 12:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9de388508190bb0ecc04740cbe15 |
completed | May 9, 2026, 2:37 a.m. |
Created at: April 10, 2026, 3 a.m.