Triple
T38176884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ann Arbor Municipal Airport |
E1000239
|
entity |
| Predicate | direction from downtown Ann Arbor |
P197380
|
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: [Ann Arbor Municipal Airport, direction from downtown Ann Arbor, south]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: direction from downtown Ann Arbor Context triple: [Ann Arbor Municipal Airport, direction from downtown Ann Arbor, south]
-
A.
directionFromGrandRapids
Indicates the cardinal or relative direction in which one entity is located from Grand Rapids.
-
B.
isDowntownEndpointOf
Indicates that a location serves as the downtown terminus or endpoint of a route, line, or path.
-
C.
directionFromColumbus
Indicates the compass direction in which one location lies when measured from Columbus.
-
D.
distanceFromCityCenterDirection
Indicates the distance and compass direction of a location relative to the center of a specified city.
-
E.
orientationRelativeToDetroit
Indicates the directional or positional orientation of one entity in relation to the location of Detroit.
- 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_69f76daaace48190a38cee37f8ce343f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fe8ddf70e48190a917eb9e8f7b6966 |
completed | May 9, 2026, 1:29 a.m. |
| PD | Predicate disambiguation | batch_69fe87ef94dc81909bb00ec8d6de9bcd |
completed | May 9, 2026, 1:03 a.m. |
| PDg | Predicate description generation | batch_69fe8dde8d008190b03dc0f97618073c |
completed | May 9, 2026, 1:29 a.m. |
Created at: May 3, 2026, 4:29 p.m.