Triple
T27089374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shane Ross |
E686118
|
entity |
| Predicate | closeProfessionalTieWith |
P116069
|
FINISHED |
| Object | Cristina Yang |
—
|
NE NERFINISHED |
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: Cristina Yang | Statement: [Shane Ross, closeProfessionalTieWith, Cristina Yang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closeProfessionalTieWith Context triple: [Shane Ross, closeProfessionalTieWith, Cristina Yang]
-
A.
closeRelationship
Indicates a strong, intimate, or emotionally significant bond between two entities, suggesting familiarity, trust, and frequent or meaningful interaction.
-
B.
closeAssociation
chosen
Indicates a strong, ongoing relationship or connection between two entities, typically involving frequent interaction, mutual influence, or shared context.
-
C.
closeAlly
Indicates a strong, trusted alliance or partnership between two entities, characterized by mutual support and cooperation.
-
D.
closer
Indicates that one entity is at a smaller distance to a reference point or object than another entity is.
-
E.
tieInWith
Indicates that one thing is connected, coordinated, or made consistent with another, often as part of a combined plan, theme, or schedule.
- 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_69ef148940ec819097b5c20fbfbf7c81 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c2f81c8190bf369226306eef09 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 27, 2026, 8:40 a.m.