Triple
T19317482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ormond Hotel episode in Ulysses |
E483135
|
entity |
| Predicate | JoyceSchemaOrgan |
P135570
|
FINISHED |
| Object | ear |
—
|
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: ear | Statement: [Ormond Hotel episode in Ulysses, JoyceSchemaOrgan, ear]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: JoyceSchemaOrgan Context triple: [Ormond Hotel episode in Ulysses, JoyceSchemaOrgan, ear]
-
A.
mayBeSubjectOf
Indicates that an entity has the potential or possibility to serve as the subject in a given relation, event, or statement.
-
B.
GoldenRecordContent
Indicates that an entity represents the canonical, authoritative version of content used as the single source of truth across systems or records.
-
C.
isIndividualOf
Indicates that a specific entity is an individual instance or member of a broader class, category, or group.
-
D.
conceptualizedBy
Indicates that something exists as an idea, model, or concept that was formed or defined by a particular agent.
-
E.
nameOf
Indicates that one entity is the name or designation of another entity.
- F. None of above. chosen
Provenance (4 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_69d8e8d13e3c81909d91d1d5ec37c095 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e60d85046c81909d972a6b369b0c2b |
completed | April 20, 2026, 11:27 a.m. |
| PD | Predicate disambiguation | batch_69e4dd0ef66881909d489d634eee817a |
completed | April 19, 2026, 1:47 p.m. |
| PDg | Predicate description generation | batch_69e4e4709d4481908c280cdd2ac18977 |
completed | April 19, 2026, 2:19 p.m. |
Created at: April 10, 2026, 1:32 p.m.