Triple
T16359839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | cross potent with four crosslets |
E397280
|
entity |
| Predicate | symbolicInterpretation |
P102883
|
FINISHED |
| Object | five wounds of Christ |
—
|
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: five wounds of Christ | Statement: [cross potent with four crosslets, symbolicInterpretation, five wounds of Christ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: symbolicInterpretation Context triple: [cross potent with four crosslets, symbolicInterpretation, five wounds of Christ]
-
A.
hasSymbolicInterpretation
chosen
Indicates that one entity is understood or used as a symbolic representation or metaphorical stand-in for another entity or concept.
-
B.
symbolizedIn
Indicates that one entity serves as a symbol or representation of another entity.
-
C.
intendedInterpretation
Indicates that one entity is meant to be understood or interpreted in a particular way, sense, or meaning relative to another.
-
D.
containsInterpretationOf
Indicates that one entity includes or embodies an interpretation or understanding of another entity.
-
E.
interpretiveConsequence
Indicates that one entity is a conclusion, implication, or interpretive outcome that follows from another entity.
- 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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2fad241848190a9f32c7b050f20a5 |
completed | April 18, 2026, 3:30 a.m. |
| PD | Predicate disambiguation | batch_69e226f37ecc819082af58b29b4e39d1 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:07 a.m.