Triple
T35931710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | al-Husn |
E1039179
|
entity |
| Predicate | heritageDesignationOfNearbyCastle |
P110459
|
FINISHED |
| Object | World Heritage Site |
—
|
NE NERFINISHED |
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: World Heritage Site | Statement: [al-Husn, heritageDesignationOfNearbyCastle, World Heritage Site]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heritageDesignationOfNearbyCastle Context triple: [al-Husn, heritageDesignationOfNearbyCastle, World Heritage Site]
-
A.
heritageStatusOfCastle
Indicates that a castle holds a particular heritage designation or protection status.
-
B.
heritageDesignationOfNearbySite
chosen
Indicates that a site has an official heritage designation specifically because of its proximity to another nearby site.
-
C.
nearbyCastle
Indicates that one entity is located close to or within a short distance of a castle.
-
D.
nearbyCastleFunction
Indicates that one entity serves as a functional or operational counterpart (such as support, service, or utility) for a castle located nearby another entity.
-
E.
heritageDesignation
Indicates that an entity has been formally assigned a specific cultural, historical, or heritage protection status by an authority.
- 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_69f76e23e4688190a5369138755138bf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd485f57dc8190820365396d041991 |
completed | May 8, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69fd47d35da081908bec8901018d186c |
completed | May 8, 2026, 2:17 a.m. |
Created at: May 3, 2026, 4:07 p.m.