Triple
T20221632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edna |
E495268
|
entity |
| Predicate | relationshipToHosts |
P54490
|
FINISHED |
| Object | friend of Agnes and Tobias |
—
|
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: friend of Agnes and Tobias | Statement: [Edna, relationshipToHosts, friend of Agnes and Tobias]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToHosts Context triple: [Edna, relationshipToHosts, friend of Agnes and Tobias]
-
A.
hostsOrganizationRelevantToRelations
Indicates that a host entity is associated with an organization that is pertinent or significant to the relationships or interactions being modeled.
-
B.
relationshipWithGuests
chosen
Indicates the nature or status of the connection or interaction that someone has with their guests.
-
C.
addressesRelationship
Indicates that one entity directs communication, remarks, or attention specifically toward another entity.
-
D.
relationshipToARP
Indicates a specified type of relationship or association that an entity has to an ARP (which may represent a particular person, program, plan, or reference point).
-
E.
relationshipToHumans
Indicates the nature or type of connection, association, or relevance that something has specifically with humans.
- 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_69da626cff80819097b530718a7c98b6 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66fd610f881908fdd22b1f8bd2efc |
completed | April 20, 2026, 6:26 p.m. |
| PD | Predicate disambiguation | batch_69e55b18609481909ab28bc8750a642f |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:39 p.m.