Triple
T38396845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eksjö |
E900785
|
entity |
| Predicate | oldTownName |
P76172
|
FINISHED |
| Object | Gamla stan i Eksjö |
—
|
NE NERFINISHED |
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: Gamla stan i Eksjö | Statement: [Eksjö, oldTownName, Gamla stan i Eksjö]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oldTownName Context triple: [Eksjö, oldTownName, Gamla stan i Eksjö]
-
A.
historicalTownName
chosen
Indicates that the object is a former or historical name by which the town (subject) was previously known.
-
B.
nearbyTownFormerName
Indicates that the nearby town previously had a different name, specifying its former name in relation to the current nearby town.
-
C.
oldTownLocatedOn
Indicates that an old town is situated on or along a particular geographic feature, such as a river, coast, or other landmark.
-
D.
oldTownStatus
Indicates that a place holds the designation or characteristics of being an old or historic town.
-
E.
nicknameOfTown
Indicates that one entity is a nickname or informal name used to refer to a particular town.
- 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_69f76e6071a081909eea7a670d21420c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.