Triple
T27870520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diaojiaolou |
E704478
|
entity |
| Predicate | typicallyBuiltOn |
P2012
|
FINISHED |
| Object | hillsides |
—
|
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: hillsides | Statement: [Diaojiaolou, typicallyBuiltOn, hillsides]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyBuiltOn Context triple: [Diaojiaolou, typicallyBuiltOn, hillsides]
-
A.
typicallyBuiltAt
Indicates the usual or most common location, context, or time at which something is constructed or created.
-
B.
builtOn
chosen
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
C.
platformBuiltAt
Indicates that a platform was constructed or established at a specific location or site.
-
D.
oftenBuiltBy
Indicates that something is frequently or commonly constructed or created by a particular agent or type of agent.
-
E.
isBuiltFor
Indicates that one entity is specifically designed, intended, or optimized to serve, support, or accommodate another entity or purpose.
- 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_69ef840f12408190b539d00d79658abf |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_6a002dd4066c8190945a09ed82f44f3f |
completed | May 10, 2026, 7:03 a.m. |
| PD | Predicate disambiguation | batch_6a002b141f4081909999e14988105f3a |
completed | May 10, 2026, 6:52 a.m. |
Created at: April 27, 2026, 6:24 p.m.