Triple
T2088505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KSAN |
E32610
|
entity |
| Predicate | hasNavigationAid |
P8170
|
FINISHED |
| Object |
SAN VORTAC
SAN VORTAC is a ground-based radio navigation facility (combining VOR and TACAN) serving the San Diego International Airport area for en-route and approach guidance.
|
E232494
|
NE FINISHED |
How this triple was built (4 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: SAN VORTAC | Statement: [KSAN, hasNavigationAid, SAN VORTAC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SAN VORTAC Context triple: [KSAN, hasNavigationAid, SAN VORTAC]
-
A.
Vinton
Vinton is the given name of Vinton Cerf, an American computer scientist widely recognized as one of the "fathers of the Internet."
-
B.
Vanne
Vanne is a river in north-central France that serves as a tributary of the Yonne.
-
C.
Faventia
Faventia is the ancient Roman name for the Italian city of Faenza, historically known as an important settlement in northern Italy.
-
D.
VGTZ station
VGTZ station is a stop on the Volgograd Metrotram system in Volgograd, Russia, serving the nearby Volgograd Tractor Plant (VGTZ) industrial area.
-
E.
Navotas
Navotas is a coastal city in the Philippines known as part of Metro Manila’s fishing and fishport hub.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SAN VORTAC Triple: [KSAN, hasNavigationAid, SAN VORTAC]
Generated description
SAN VORTAC is a ground-based radio navigation facility (combining VOR and TACAN) serving the San Diego International Airport area for en-route and approach guidance.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SAN VORTAC Target entity description: SAN VORTAC is a ground-based radio navigation facility (combining VOR and TACAN) serving the San Diego International Airport area for en-route and approach guidance.
-
A.
Vinton
Vinton is the given name of Vinton Cerf, an American computer scientist widely recognized as one of the "fathers of the Internet."
-
B.
Vanne
Vanne is a river in north-central France that serves as a tributary of the Yonne.
-
C.
Faventia
Faventia is the ancient Roman name for the Italian city of Faenza, historically known as an important settlement in northern Italy.
-
D.
VGTZ station
VGTZ station is a stop on the Volgograd Metrotram system in Volgograd, Russia, serving the nearby Volgograd Tractor Plant (VGTZ) industrial area.
-
E.
Navotas
Navotas is a coastal city in the Philippines known as part of Metro Manila’s fishing and fishport hub.
- F. None of above. chosen
Provenance (5 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_69a885eba0708190999696a45cbec816 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abba712388819091d68a4bb99f6b17 |
completed | March 7, 2026, 5:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae2742834c8190ad9be71128959e0c |
completed | March 9, 2026, 1:49 a.m. |
| NEDg | Description generation | batch_69ae2bd9c41c819089f65019e2fb93ad |
completed | March 9, 2026, 2:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae2c61c3e08190a0ab44db0af9eb55 |
completed | March 9, 2026, 2:11 a.m. |
Created at: March 4, 2026, 7:43 p.m.