Triple
T28878678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zana |
E732351
|
entity |
| Predicate | guardianInFiction |
P82919
|
FINISHED |
| Object | David Bryan |
—
|
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: David Bryan | Statement: [Zana, guardianInFiction, David Bryan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardianInFiction Context triple: [Zana, guardianInFiction, David Bryan]
-
A.
guardian
Indicates a protective or custodial relationship in which one entity is responsible for the care, safety, or oversight of another.
-
B.
guardedByInFiction
chosen
Indicates that one fictional entity is protected or watched over by another within a narrative context.
-
C.
guardianDeitiesOrFigures
Indicates a protective or watchful relationship in which certain deities or figures serve as guardians over specific people, places, objects, or domains.
-
D.
threatenedByInFiction
Indicates that, within a fictional context, one entity is portrayed as being threatened by another entity.
-
E.
hasGuardianCharacter
Indicates that one entity serves as a guardian or protective character for another entity.
- 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_69f05b06807c81909b4bbd4c20403a2b |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65b14512c8190a40e70319dcc54cd |
completed | May 2, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 7:40 a.m.