Triple
T20384222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Wizard’s palace |
E497918
|
entity |
| Predicate | visitedBy |
P1096
|
FINISHED |
| Object | Cowardly Lion |
—
|
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: Cowardly Lion | Statement: [The Wizard’s palace, visitedBy, Cowardly Lion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cowardly Lion Context triple: [The Wizard’s palace, visitedBy, Cowardly Lion]
-
A.
The Cowardly Lion
chosen
The Cowardly Lion is a fictional lion from L. Frank Baum’s Oz stories, best known as Dorothy’s timid yet ultimately brave companion in "The Wizard of Oz."
-
B.
Zazu
Zazu is the uptight yet loyal red-billed hornbill who serves as Mufasa’s majordomo in Disney’s The Lion King.
-
C.
The Tin Man
The Tin Man is a beloved fictional character from L. Frank Baum’s Oz stories, best known as the heart-seeking, metal woodsman who journeys with Dorothy to see the Wizard.
-
D.
The Flying Monkey
The Flying Monkey is a historic movie house and live performance venue known for hosting films, concerts, and cultural events.
-
E.
The Scarecrow
The Scarecrow is a work best known as a notable creation of writer Joe Roberts.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4a5b7908190a972e4e7e698ae94 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678b2ceec819091ad5205ee9b2174 |
completed | April 20, 2026, 7:04 p.m. |
Created at: April 16, 2026, 11:27 a.m.