Triple
T27326127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ignacio, Colorado |
E689648
|
entity |
| Predicate | distanceToDurango |
P199366
|
FINISHED |
| Object | about 20 miles southeast of Durango |
—
|
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: about 20 miles southeast of Durango | Statement: [Ignacio, Colorado, distanceToDurango, about 20 miles southeast of Durango]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceToDurango Context triple: [Ignacio, Colorado, distanceToDurango, about 20 miles southeast of Durango]
-
A.
distanceFromDenver
Indicates the measured distance between a given location and Denver.
-
B.
distanceToPueblo
Indicates the measured spatial distance between a given entity and the location identified as Pueblo.
-
C.
distanceToPonchaSprings
Indicates the measured distance between a given entity’s location and the location of Poncha Springs.
-
D.
approxDistanceToColoradoSprings
Indicates that one entity is located at an approximate physical distance from Colorado Springs.
-
E.
distanceFromSocorro
Indicates the spatial distance between an entity and the reference location Socorro.
- 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_69ef355d4cb08190ab032c0a2e7d3753 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69ff32b88bf48190b45afd1b60cb511c |
completed | May 9, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69ff3031e18881908927b2ab452de863 |
completed | May 9, 2026, 1:01 p.m. |
| PDg | Predicate description generation | batch_69ff32b6dd448190a7a6ebb76b99d4cc |
completed | May 9, 2026, 1:12 p.m. |
Created at: April 27, 2026, 11:35 a.m.