Triple
T33265227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proteus |
E851624
|
entity |
| Predicate | relationshipTypeWithJulia |
P138296
|
FINISHED |
| Object | faithless lover |
—
|
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: faithless lover | Statement: [Proteus, relationshipTypeWithJulia, faithless lover]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithJulia Context triple: [Proteus, relationshipTypeWithJulia, faithless lover]
-
A.
relationshipToJulia
chosen
Indicates the specific type of personal or social relationship that an entity has with Julia.
-
B.
relationshipToJulie
Indicates a specified type of relationship or connection that an entity has to Julie.
-
C.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
-
D.
relationshipTypeWithJulie d’Étange
Indicates the specific nature or category of the relationship that an entity has with Julie d’Étange.
-
E.
relationshipTypeWithKatnissEverdeen
Indicates the type or nature of the relationship an entity has with Katniss Everdeen.
- 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_69f349642dac81908a37ffcc3b976a55 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f338b881908e5593e45d764f4d |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:32 a.m.