Triple
T34027305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Juwanna Mann |
E872543
|
entity |
| Predicate | fictionalWomenLeague |
P129655
|
FINISHED |
| Object | WUBA |
—
|
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: WUBA | Statement: [Juwanna Mann, fictionalWomenLeague, WUBA]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fictionalWomenLeague Context triple: [Juwanna Mann, fictionalWomenLeague, WUBA]
-
A.
fictionalLeague
chosen
Indicates that an entity is associated with or belongs to a league that exists only in fiction rather than in reality.
-
B.
womenCounterpartLeague
Indicates that one league is the women’s counterpart or equivalent of another (typically men’s) league.
-
C.
includesWomen'sLeagues
Indicates that the subject entity encompasses, offers, or is associated with one or more leagues specifically organized for women.
-
D.
featuresWomenTeams
Indicates that the subject includes, presents, or involves teams composed of women.
-
E.
fictionalPlayer
Indicates that the referenced player entity is imaginary or does not exist in the real world, but is instead part of a fictional or simulated context.
- 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_69f349a2527c81909a7cd4bda94d70ad |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69feafa1ba0081909013800b85a9f613 |
completed | May 9, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69feae58d62c81909d031f3df8992883 |
completed | May 9, 2026, 3:47 a.m. |
Created at: May 1, 2026, 1:51 a.m.