Triple
T4684470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaziantep Castle |
E103885
|
entity |
| Predicate | majorRestorationCentury |
P10303
|
FINISHED |
| Object | 6th century |
—
|
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: 6th century | Statement: [Gaziantep Castle, majorRestorationCentury, 6th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorRestorationCentury Context triple: [Gaziantep Castle, majorRestorationCentury, 6th century]
-
A.
majorRestorationLocation
Indicates the primary place where a significant restoration or refurbishment of an object, structure, or work was carried out.
-
B.
partiallyRebuiltInCentury
Indicates that an entity underwent partial reconstruction or significant repair during the specified century.
-
C.
rebuiltInCentury
Indicates that an existing structure or entity was reconstructed or significantly rebuilt during a specified century.
-
D.
constructionCentury
Indicates the century during which something was constructed or built.
-
E.
century
chosen
Indicates that an entity is associated with, occurs in, or belongs to a particular 100-year time period.
- 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_69bd43debbf08190b4bc372e286ec234 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd67c9c3c08190a6c4944cdd1362a8 |
completed | March 20, 2026, 3:29 p.m. |
| PD | Predicate disambiguation | batch_69bd6217e0088190836570522e324dc6 |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:16 p.m.