Triple
T16523169
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annunciation mosaic |
E401370
|
entity |
| Predicate | depicts |
P1581
|
FINISHED |
| Object | angel Gabriel |
E8490
|
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: angel Gabriel | Statement: [Annunciation mosaic, depicts, angel Gabriel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: angel Gabriel Context triple: [Annunciation mosaic, depicts, angel Gabriel]
-
A.
angel
An angel is a supernatural being or messenger of God found in various religious traditions, often depicted as a powerful, benevolent spirit that interacts with humans.
-
B.
Gabriel
chosen
Gabriel is a common masculine given name of Hebrew origin, widely used in many cultures and languages.
-
C.
Angel
An angel is a spiritual being found in various religious traditions, typically depicted as a messenger or servant of the divine.
-
D.
Angel
Angel is a fictional character who is part of the Whole Sick Crew in Thomas Pynchon's novel "V."
-
E.
Angel
Angel is an American supernatural drama television series set in the Buffy the Vampire Slayer universe, following a vampire with a soul seeking redemption in Los Angeles.
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32ed2622c8190b6429a49ca92284a |
completed | April 18, 2026, 7:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00608b7f6081909912dd575979f8d7 |
completed | May 10, 2026, 10:40 a.m. |
Created at: April 10, 2026, 5:14 a.m.