Triple
T38397523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Department of Computer Science, Lund University |
E900800
|
entity |
| Predicate | isInUniversityTown |
P4747
|
FINISHED |
| Object | Lund |
—
|
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: Lund | Statement: [Department of Computer Science, Lund University, isInUniversityTown, Lund]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInUniversityTown Context triple: [Department of Computer Science, Lund University, isInUniversityTown, Lund]
-
A.
containsUniversityCity
Indicates that a given region or area includes within its boundaries a city that hosts a university.
-
B.
hasCollegeTown
Indicates that a college or university is associated with, or located in, a particular town that serves as its college town.
-
C.
hasUniversityArea
Indicates that a specified area or region is designated as the university area associated with a given entity.
-
D.
hasCampusTownCharacter
Indicates that a place exhibits qualities or atmosphere typically associated with a college or university town.
-
E.
isCollegeTownOf
chosen
Indicates that a town or city is primarily known for and significantly shaped by the presence of a particular college or university.
- 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.