Triple
T840392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Origen |
E18162
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Hexapla |
E100381
|
NE 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: Hexapla | Statement: [Origen, notableWork, Hexapla]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hexapla Context triple: [Origen, notableWork, Hexapla]
-
A.
Hexapla
chosen
Hexapla is a massive critical edition of the Hebrew Bible compiled by the early Christian scholar Origen, presenting multiple parallel Greek and Hebrew text versions for comparative study.
-
B.
Septuagint
The Septuagint is an ancient Greek translation of the Hebrew Scriptures that became the primary Old Testament text for early Christians and Greek-speaking Jews.
-
C.
Peshitta
The Peshitta is the standard Syriac version of the Bible, historically central to Syriac Christianity’s scripture and liturgy.
-
D.
Codex Bezae
Codex Bezae is a 5th-century Greek-Latin bilingual manuscript of the New Testament, notable for its distinctive textual variants and importance in biblical textual criticism.
-
E.
Codex Sinaiticus
Codex Sinaiticus is one of the oldest and most complete surviving manuscripts of the Christian Bible, written in Greek on parchment in the 4th century.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a49389f44881909a608fb27d89f247 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4abe5d7848190b15e0cb343b6f4ba |
completed | March 1, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7a3bb2fa08190b1e8f26ceb04b08c |
completed | March 4, 2026, 3:15 a.m. |
Created at: March 1, 2026, 7:38 p.m.