Triple
T6818450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tiāntán |
E156830
|
entity |
| Predicate | hasEnclosingFeature |
P15848
|
FINISHED |
| Object | double wall layout |
—
|
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: double wall layout | Statement: [Tiāntán, hasEnclosingFeature, double wall layout]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEnclosingFeature Context triple: [Tiāntán, hasEnclosingFeature, double wall layout]
-
A.
hasEnclosures
chosen
Indicates that an entity possesses or contains one or more enclosing structures, spaces, or bounded areas associated with it.
-
B.
hasBoundaryFeature
Indicates that a boundary (such as an edge, border, or limit) of one entity is characterized, marked, or defined by a specific feature or element.
-
C.
hasOriginFeature
Indicates that an entity possesses a specific characteristic, attribute, or feature related to its origin or source.
-
D.
hasFeatureID
Indicates that an entity is associated with a specific feature identified by a unique ID.
-
E.
isFeatureOf
Indicates that something functions as a characteristic, attribute, or component belonging to or describing another entity.
- 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_69c688298a288190af3f285d57f76bbe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d355b52081909f037cec76bdccf6 |
completed | March 27, 2026, 6:58 p.m. |
| PD | Predicate disambiguation | batch_69c6d09bb4f881909bf20c188cb3e8e1 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:17 p.m.