Triple
T12948447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexander’s Prison (Zendan-e Eskandar) |
E309827
|
entity |
| Predicate | cityFamousFor |
P7335
|
FINISHED |
| Object | Yazd’s mud-brick and brick architecture |
—
|
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: Yazd’s mud-brick and brick architecture | Statement: [Alexander’s Prison (Zendan-e Eskandar), cityFamousFor, Yazd’s mud-brick and brick architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cityFamousFor Context triple: [Alexander’s Prison (Zendan-e Eskandar), cityFamousFor, Yazd’s mud-brick and brick architecture]
-
A.
primaryCityLandmarkOf
Indicates that a landmark is a principal or defining landmark associated with a specific city.
-
B.
cityRecognizedBy
Indicates that a city has been formally acknowledged, certified, or granted status by a particular authority, organization, or governing body.
-
C.
hasFamousCity
Indicates that an entity possesses or is associated with a city that is widely recognized or renowned.
-
D.
touristAttractionIn
chosen
Indicates that a place functions as a tourist attraction located within a specified geographic area or entity.
-
E.
notableInCity
Indicates that an entity is particularly prominent, recognized, or significant within a specific city.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97db69f548190a1a693bc0d6c191a |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:43 p.m.