Triple
T28503915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maxim Gorky |
E721318
|
entity |
| Predicate | eventHostedRole |
P4073
|
FINISHED |
| Object | meeting place for heads of state |
—
|
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: meeting place for heads of state | Statement: [Maxim Gorky, eventHostedRole, meeting place for heads of state]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eventHostedRole Context triple: [Maxim Gorky, eventHostedRole, meeting place for heads of state]
-
A.
eventRole
chosen
Indicates the specific function, capacity, or part an entity plays within an event or occurrence.
-
B.
organizerRole
Indicates that an entity has the role or responsibility of organizing an event, activity, or group.
-
C.
roleOfHost
Indicates that an entity serves as the host in relation to another entity, event, or interaction.
-
D.
bookingRole
Indicates the role or capacity an entity has in relation to a booking (e.g., who made, manages, or is responsible for the booking).
-
E.
conferenceHost
Indicates that an entity serves as the organizer or host responsible for running or managing a conference for another entity.
- 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_69f01a5c072081908c7b04bcf6478da9 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6617ba4a88190bfc5c305acb4f93f |
completed | May 2, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f660f082508190a95a7888ad66cb2e |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 3:08 a.m.