Triple
T27349792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maarva Andor |
E684322
|
entity |
| Predicate | adoptiveRelationshipType |
P164499
|
FINISHED |
| Object | rescued Cassian from Kenari |
—
|
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: rescued Cassian from Kenari | Statement: [Maarva Andor, adoptiveRelationshipType, rescued Cassian from Kenari]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adoptiveRelationshipType Context triple: [Maarva Andor, adoptiveRelationshipType, rescued Cassian from Kenari]
-
A.
adoptiveParent
Indicates that one entity is the legally recognized parent of another through adoption rather than biological descent.
-
B.
parentalRelationshipStatusAtAdoption
Indicates the type and condition of the parent–child relationship that existed at the time the adoption took place.
-
C.
adoptiveStructure
Indicates a structural relationship where one entity has been adopted into, or functions as, the adopted counterpart of another entity within a system or hierarchy.
-
D.
adoptiveFamily
Indicates a familial relationship formed through legal adoption rather than biological descent.
-
E.
adoptiveChild
Indicates that one entity is the child of another through legal adoption rather than biological descent.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f64e6e8c9081908ce4d364aa26147a |
completed | May 2, 2026, 7:20 p.m. |
| PD | Predicate disambiguation | batch_69f64cacd2c08190aed8a1761d0da679 |
completed | May 2, 2026, 7:12 p.m. |
| PDg | Predicate description generation | batch_69f64db8ee1881909362701d72ffe282 |
completed | May 2, 2026, 7:17 p.m. |
Created at: April 27, 2026, 11:48 a.m.