Triple
T17596703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madrid Union Assembly |
E428589
|
entity |
| Predicate | holdsSession |
P1266
|
FINISHED |
| Object | ordinary sessions |
—
|
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: ordinary sessions | Statement: [Madrid Union Assembly, holdsSession, ordinary sessions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holdsSession Context triple: [Madrid Union Assembly, holdsSession, ordinary sessions]
-
A.
heldSessionsIn
Indicates that an entity organized or conducted one or more sessions, meetings, or events at a specified location or venue.
-
B.
inSessionDuring
Indicates that an entity is actively engaged in or part of a session throughout a specified time period.
-
C.
sessionOf
Indicates that one entity is a session that belongs to, occurs within, or is associated with another entity (such as an event, course, or meeting series).
-
D.
hasSession
chosen
Indicates that an entity is associated with, participates in, or contains a particular session instance.
-
E.
holdsService
Indicates that one entity provides, maintains, or is responsible for a particular service for another entity or context.
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e469ec335c8190abcaff700cfff23b |
completed | April 19, 2026, 5:36 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fff0348190b899a32da537eaca |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:51 a.m.