Triple
T29182824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Simon Belmont |
E739787
|
entity |
| Predicate | canonicalWhip |
P122765
|
FINISHED |
| Object | Vampire Killer |
—
|
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: Vampire Killer | Statement: [Simon Belmont, canonicalWhip, Vampire Killer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canonicalWhip Context triple: [Simon Belmont, canonicalWhip, Vampire Killer]
-
A.
whips
Indicates that one entity strikes or lashes another entity using a whip or whip-like implement.
-
B.
hasWhips
Indicates that one entity possesses, controls, or is equipped with one or more whips in relation to another entity or context.
-
C.
typeOfWhip
chosen
Indicates that one entity is a specific kind or category of whip in relation to another entity.
-
D.
hasMajorityWhip
Indicates that one entity serves as the majority whip (the chief vote-counter and party discipline enforcer for the majority party) for another legislative body or group.
-
E.
canonicalText
Indicates that a standardized, authoritative textual representation is associated with an entity or expression.
- 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_69f07cb74c2c8190ad396487fcb4fde6 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f66384473c81909fb9ff9037f56b67 |
completed | May 2, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:58 a.m.