Triple
T338019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chi-Rho monogram |
E6770
|
entity |
| Predicate | firstLetterOf |
P3818
|
FINISHED |
| Object | Greek word "Χριστός" |
—
|
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: Greek word "Χριστός" | Statement: [Chi-Rho monogram, firstLetterOf, Greek word "Χριστός"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstLetterOf Context triple: [Chi-Rho monogram, firstLetterOf, Greek word "Χριστός"]
-
A.
firstLetter
chosen
Indicates that one entity is the initial character or starting letter of another entity (typically a string or word).
-
B.
firstOf
Indicates that one entity is the earliest or initial member in an ordered sequence or collection relative to the others.
-
C.
firstLitAt
Indicates that a particular object or location becomes illuminated or receives light for the first time at a specified time or under specified conditions.
-
D.
letterCase
Indicates the relationship between a character or string and its typographical case (such as uppercase, lowercase, or mixed case).
-
E.
middleNameInitial
Indicates that one entity is the initial letter of the middle name of 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_69a2e79434908190a9d5afe415153ad9 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eae23b0c819081f8bf9ac26685ab |
completed | Feb. 28, 2026, 1:17 p.m. |
| PD | Predicate disambiguation | batch_69a2e95067e88190a914a1c1d0283dfc |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.