Triple
T10090363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Erasmus Craven |
E215325
|
entity |
| Predicate | entangledIn |
P91259
|
FINISHED |
| Object | magical rivalry |
—
|
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: magical rivalry | Statement: [Dr. Erasmus Craven, entangledIn, magical rivalry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: entangledIn Context triple: [Dr. Erasmus Craven, entangledIn, magical rivalry]
-
A.
entangledWith
Indicates a mutual state in which two or more entities are so interconnected that a change or condition in one inherently affects or constrains the other(s).
-
B.
canBeEntangledIn
chosen
Indicates that one entity is capable of becoming physically or conceptually caught, intertwined, or ensnared within another entity or situation.
-
C.
engaged
Indicates that two entities are formally committed to enter into a marriage or long-term partnership with each other.
-
D.
engagedTo
Indicates that two entities are formally committed to marry each other.
-
E.
heldTogetherWith
Indicates that two or more entities are physically joined or kept in contact by some binding, fastening, or cohesive force.
- 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_69ca83a1eed081908b2e9580f2ebeea7 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd05960008190baecb8e4c9f2461f |
completed | April 2, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9b853c8190a2af993ce9b21309 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:01 p.m.