Triple
T30252319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bilis Manger |
E769236
|
entity |
| Predicate | settingLinkedTo |
P44691
|
FINISHED |
| Object | Cardiff |
—
|
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: Cardiff | Statement: [Bilis Manger, settingLinkedTo, Cardiff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: settingLinkedTo Context triple: [Bilis Manger, settingLinkedTo, Cardiff]
-
A.
linkedByServiceTo
Indicates that one entity is connected or associated with another through a specific service acting as the linking mechanism.
-
B.
settingRelation
Indicates a contextual relationship where one entity serves as the environment, backdrop, or situational context in which another entity exists or an event occurs.
-
C.
styleLinkedTo
Indicates a relationship where one style is associated with, derived from, or otherwise connected to another style.
-
D.
deFactoLinkedWith
Indicates that two entities are informally or practically associated or connected, even if there is no official or legally recognized relationship between them.
-
E.
associatedWithSetting
chosen
Indicates that one entity is connected or linked to a particular context, environment, or setting in which it occurs or is relevant.
- 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_69f224831dc08190b2e569b987264057 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f7308a096081909d66a56f3c926806 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69f72a00c5f081908b6539d15baf4e12 |
completed | May 3, 2026, 10:57 a.m. |
Created at: April 29, 2026, 7:40 p.m.