Triple
T15393874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dromi |
E368118
|
entity |
| Predicate | follows |
P134
|
FINISHED |
| Object | Læding |
E1156026
|
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: Læding | Statement: [Dromi, follows, Læding]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Læding Context triple: [Dromi, follows, Læding]
-
A.
Læding
chosen
Læding is one of the earlier chains from Norse mythology that the gods used in their attempts to bind the monstrous wolf Fenrir before ultimately resorting to the magical fetter Gleipnir.
-
B.
Lødingen
Lødingen is a coastal municipality in Nordland county, Norway, located on the island of Hinnøya and known for its fishing, maritime activities, and scenic fjord landscape.
-
C.
Lokstedt
Lokstedt is a district in the Eimsbüttel borough of Hamburg, Germany, known for its residential character and the presence of major broadcasting facilities.
-
D.
Lindhagen
Lindhagen is a Swedish surname most notably associated with the politician and social reformer Carl Lindhagen.
-
E.
Lillesand
Lillesand is a small coastal town and municipality in Agder county, Norway, known for its white wooden houses, maritime heritage, and popular summer tourism along the Skagerrak coast.
- 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_69d85a1551a08190ba2caea7cd51c639 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e7838b48190862b43c6c8620692 |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff219a285481909eef3ec6e523573c |
completed | May 9, 2026, 11:59 a.m. |
Created at: April 10, 2026, 3:19 a.m.