Triple
T32022557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of a Man in a Red Turban |
E817732
|
entity |
| Predicate | dateInscribed |
P33351
|
FINISHED |
| Object | 21 October 1433 |
—
|
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: 21 October 1433 | Statement: [Portrait of a Man in a Red Turban, dateInscribed, 21 October 1433]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateInscribed Context triple: [Portrait of a Man in a Red Turban, dateInscribed, 21 October 1433]
-
A.
inscribedOn
Indicates that text, symbols, or markings are written or carved onto the surface of an object.
-
B.
inscribedAt
Indicates that an entity is formally recorded, registered, or written onto a specific object, surface, or official list at a particular place or institution.
-
C.
firstInscriptionYear
Indicates the year in which an entity was first inscribed, recorded, or officially entered into a relevant register or list.
-
D.
dateDepicted
Indicates that one entity specifies the calendar date on which the other entity, typically an event or scene, is depicted as occurring.
-
E.
inscriptionDate
chosen
Indicates the date on which an inscription was created, carved, or formally recorded.
- 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_69f348fb04e4819081f4eab040ed7959 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b467759c8190905ba0ce0eceb5fb |
completed | May 3, 2026, 2:35 a.m. |
| PD | Predicate disambiguation | batch_69f6b151ad008190836c1bcdec503ce2 |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:17 a.m.