Triple
T31725501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savannah Curtis |
E809701
|
entity |
| Predicate | relationshipTypeWithJohnTyree |
P207504
|
FINISHED |
| Object | on-and-off romantic relationship |
—
|
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: on-and-off romantic relationship | Statement: [Savannah Curtis, relationshipTypeWithJohnTyree, on-and-off romantic relationship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithJohnTyree Context triple: [Savannah Curtis, relationshipTypeWithJohnTyree, on-and-off romantic relationship]
-
A.
relationshipTypeWithJohnLuther
Indicates the specific nature or category of the relationship an entity has with John Luther.
-
B.
relationshipTypeWithJohnHartigan
Indicates the specific nature or category of relationship that an entity has with John Hartigan.
-
C.
relationshipTypeWithJackieTaylor
Indicates the specific type or nature of the relationship that an entity has with Jackie Taylor.
-
D.
relationshipTypeWith Alicia Johns
Indicates the specific type or nature of the relationship that an entity has with Alicia Johns.
-
E.
relationshipTypeWith Ty Davis Jr.
Indicates the specific nature or category of the relationship that an entity has with Ty Davis Jr.
- 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_69f348e009c8819095d77df52c645b9c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e7aa0c8190bdc9ee4d54fc821b |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c7ee0388190a29faeb5cdb0950a |
completed | May 12, 2026, 7:16 p.m. |
Created at: April 30, 2026, 11:19 p.m.