Triple
T29079519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donna Troy |
E733933
|
entity |
| Predicate | sisterFigureTo |
P14414
|
FINISHED |
| Object | Wonder Woman |
—
|
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: Wonder Woman | Statement: [Donna Troy, sisterFigureTo, Wonder Woman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sisterFigureTo Context triple: [Donna Troy, sisterFigureTo, Wonder Woman]
-
A.
sisterBody
Indicates that one celestial body is considered a counterpart or closely related “sibling” to another, typically due to similar characteristics, origin, or shared system.
-
B.
sisterBase
chosen
Indicates that one entity is the sister of another, sharing at least one parent and being female relative to the other entity.
-
C.
sibling
Indicates that two entities share at least one parent, making them brothers or sisters to each other.
-
D.
sisterModule
Indicates that two modules share a common parent or grouping, making them parallel or peer components within the same larger structure.
-
E.
sisterTerminal
Indicates that two terminals share a sibling-like relationship, typically meaning they are distinct but related endpoints within the same larger system or structure.
- 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_69f05b0c0f28819086eae6e84f2ae472 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f66142a7dc8190a574168fff93191f |
completed | May 2, 2026, 8:40 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 10:53 a.m.