Triple
T11162218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas the Apostle |
E264064
|
entity |
| Predicate | biblicalEpisode |
P29938
|
FINISHED |
| Object | John 20:24–29 |
—
|
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: John 20:24–29 | Statement: [Thomas the Apostle, biblicalEpisode, John 20:24–29]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: biblicalEpisode Context triple: [Thomas the Apostle, biblicalEpisode, John 20:24–29]
-
A.
gospelEpisode
Indicates that one entity is an episode or segment within a gospel narrative or gospel-related series associated with another entity.
-
B.
episodeOfResurrection
Indicates a relationship where an event or narrative segment depicts or centers on a resurrection.
-
C.
scripturalEvent
chosen
Indicates that an event is described, referenced, or established within a scriptural or sacred text.
-
D.
scriptureFocus
Indicates that something centers on, emphasizes, or is primarily concerned with religious scripture or sacred texts.
-
E.
scriptureFor
Indicates that one entity serves as a scriptural or authoritative religious text for another entity (such as a person, group, or belief system).
- 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_69d6aa9ccddc8190868998c8b7beb060 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8832fe88190a74d81f9ed547baa |
completed | April 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69d75cec26fc8190a5497d186306f935 |
completed | April 9, 2026, 8:01 a.m. |
Created at: April 8, 2026, 9:29 p.m.