Triple
T5858121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Hills |
E130205
|
entity |
| Predicate | directionFromPittsburgh |
P67528
|
FINISHED |
| Object | south |
—
|
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: south | Statement: [South Hills, directionFromPittsburgh, south]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directionFromPittsburgh Context triple: [South Hills, directionFromPittsburgh, south]
-
A.
directionFromChicago
Indicates the cardinal or relative compass direction of an entity’s location measured from Chicago.
-
B.
directionFromBaltimore
Indicates the compass direction or relative bearing of one place or object when measured starting from Baltimore.
-
C.
directionFromBoston
Indicates the compass direction or bearing of one location as measured outward from Boston.
-
D.
directionFromParis
Indicates the cardinal or relative compass direction of an entity as measured from Paris toward that entity.
-
E.
directionFromSanFrancisco
Indicates the compass direction in which one location lies relative to San Francisco.
- F. None of above. chosen
Provenance (4 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_69c0084f3bb08190a7720f55f7aa4252 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c044ab0a048190b84be40fb13c0f50 |
completed | March 22, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69c03345ca0c819081c81148d054fed2 |
completed | March 22, 2026, 6:21 p.m. |
| PDg | Predicate description generation | batch_69c044a9c4f0819081b8c196932883f6 |
completed | March 22, 2026, 7:36 p.m. |
Created at: March 22, 2026, 3:56 p.m.