Triple
T38107994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pardoner |
E951574
|
entity |
| Predicate | preachesAgainst |
P33291
|
FINISHED |
| Object | avarice |
—
|
LITERAL FINISHED |
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: avarice | Statement: [Pardoner, preachesAgainst, avarice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preachesAgainst Context triple: [Pardoner, preachesAgainst, avarice]
-
A.
preachesFrom
Indicates that a person delivers a sermon, teaching, or religious message using a particular text, source, or location as the basis.
-
B.
preached
Indicates that one entity delivered a religious or moral message or sermon to others.
-
C.
advocatesAgainst
chosen
Indicates that one entity actively opposes, argues against, or campaigns to prevent or stop another entity, action, or idea.
-
D.
opposesDeity
Indicates a relationship where an entity is in conflict with, resists, or acts against a deity.
-
E.
religiousHypocrisy
Indicates a relationship where an entity’s professed religious beliefs or moral standards conflict with, and are contradicted by, its actual behavior or practices.
- 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_69f76f065ed08190bdfb1b6d817f5b39 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.