Triple
T34248623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billie Dawn |
E878670
|
entity |
| Predicate | relationshipTypeWith Harry Brock |
P131072
|
FINISHED |
| Object | girlfriend |
—
|
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: girlfriend | Statement: [Billie Dawn, relationshipTypeWith Harry Brock, girlfriend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWith Harry Brock Context triple: [Billie Dawn, relationshipTypeWith Harry Brock, girlfriend]
-
A.
relationshipToHarryBright
Indicates that one entity has a specified personal or familial relationship to the person identified as Harry Bright.
-
B.
relationshipToHarry
chosen
Indicates the specific type of relationship or connection that an entity has to Harry.
-
C.
relationshipToHarryMonroe
Indicates the specific type of personal, social, or familial relationship that one entity has to Harry Monroe.
-
D.
relationshipTypeWith Hank Evans
Indicates the specific nature or category of the relationship that an entity has with Hank Evans.
-
E.
relationshipTypeWith Alonzo Harris
Indicates the specific nature or category of the relationship that an entity has with Alonzo Harris.
- 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_69f349b3618481909df955b063f305b2 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fbe4a08190bfe65ebd141164e9 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:56 a.m.