Triple
T33106040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German trade unions |
E847192
|
entity |
| Predicate | areOrganizedIn |
P8619
|
FINISHED |
| Object | confederations |
—
|
LITERAL 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: confederations | Statement: [German trade unions, areOrganizedIn, confederations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: areOrganizedIn Context triple: [German trade unions, areOrganizedIn, confederations]
-
A.
organisedIn
chosen
Indicates that an event, activity, or entity is arranged, coordinated, or held within a particular place, context, or organizational framework.
-
B.
areOrganizedBy
Indicates that one entity is responsible for planning, coordinating, or managing the structure or execution of another entity or event.
-
C.
isOrganizedThrough
Indicates that an activity, event, or process is arranged, coordinated, or carried out by means of a particular intermediary, structure, or channel.
-
D.
oftenOrganizedBy
Indicates that an event, activity, or process is frequently arranged, coordinated, or hosted by a particular agent or entity.
-
E.
organizedAt
Indicates that an event or activity was arranged, planned, or hosted at a specific location or venue.
- 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_69f3495686508190b76bf20fa5e00bf7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6e69e388190b2d3e90b11277232 |
completed | May 3, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:26 a.m.