Triple
T19567650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apologies of Justin Martyr |
E489624
|
entity |
| Predicate | defendsPractice |
P40990
|
FINISHED |
| Object | Christian worship |
—
|
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: Christian worship | Statement: [Apologies of Justin Martyr, defendsPractice, Christian worship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defendsPractice Context triple: [Apologies of Justin Martyr, defendsPractice, Christian worship]
-
A.
defends
Indicates that one entity protects or supports another entity against attack, criticism, or harm.
-
B.
defendedWork
Indicates that one entity formally supported or justified the work, ideas, or output of another entity, typically in response to criticism or evaluation.
-
C.
defendedAs
Indicates that one entity is presented, argued, or justified as being equivalent to or serving the role of another entity in a defensive or protective context.
-
D.
defendsConcept
chosen
Indicates that one entity actively supports and argues in favor of a particular concept, idea, or theory, often in response to criticism or challenge.
-
E.
defendedLawProvision
Indicates that an entity actively supported or argued in favor of a specific provision within a law, typically in a legal or legislative 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63f79adf08190b1c0b008f30b0acd |
completed | April 20, 2026, 3 p.m. |
| PD | Predicate disambiguation | batch_69e514d4df3c8190b7e9b3b4fdf9452a |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:42 p.m.