Triple
T1548227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jorhat |
E33026
|
entity |
| Predicate | vehicleRegistrationCode |
P1173
|
FINISHED |
| Object |
AS-03
AS-03 is the regional vehicle registration code assigned to motor vehicles registered in Jorhat, a district in the Indian state of Assam.
|
E176412
|
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: AS-03 | Statement: [Jorhat, vehicleRegistrationCode, AS-03]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AS-03 Context triple: [Jorhat, vehicleRegistrationCode, AS-03]
-
A.
SA3
SA3 is the 3GPP security working group responsible for specifying and evolving security architecture and mechanisms across mobile communication standards.
-
B.
A73
A73 is a major German autobahn in Bavaria and Thuringia that links cities such as Lichtenfels with the broader national motorway network.
-
C.
C-3
C-3 is one of the main commuter rail lines in the Cercanías Madrid network, connecting central Madrid with several southern suburbs and surrounding municipalities.
-
D.
OSD(A&S)
OSD(A&S) is the U.S. Department of Defense organization responsible for overseeing defense acquisition, procurement, and sustainment of military systems and services.
-
E.
A3C
A3C (Asynchronous Advantage Actor-Critic) is a reinforcement learning algorithm that trains multiple parallel agents to learn policies and value functions efficiently using asynchronous gradient updates.
- 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: AS-03 Triple: [Jorhat, vehicleRegistrationCode, AS-03]
Generated description
AS-03 is the regional vehicle registration code assigned to motor vehicles registered in Jorhat, a district in the Indian state of Assam.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: AS-03 Target entity description: AS-03 is the regional vehicle registration code assigned to motor vehicles registered in Jorhat, a district in the Indian state of Assam.
-
A.
SA3
SA3 is the 3GPP security working group responsible for specifying and evolving security architecture and mechanisms across mobile communication standards.
-
B.
A73
A73 is a major German autobahn in Bavaria and Thuringia that links cities such as Lichtenfels with the broader national motorway network.
-
C.
C-3
C-3 is one of the main commuter rail lines in the Cercanías Madrid network, connecting central Madrid with several southern suburbs and surrounding municipalities.
-
D.
OSD(A&S)
OSD(A&S) is the U.S. Department of Defense organization responsible for overseeing defense acquisition, procurement, and sustainment of military systems and services.
-
E.
A3C
A3C (Asynchronous Advantage Actor-Critic) is a reinforcement learning algorithm that trains multiple parallel agents to learn policies and value functions efficiently using asynchronous gradient updates.
- 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_69a885ee6db8819099502bc5ce8af881 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90856642c81909d88a679eb265b10 |
completed | March 5, 2026, 4:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad30a073bc8190a269cb036775dfe4 |
completed | March 8, 2026, 8:17 a.m. |
| NEDg | Description generation | batch_69ad3117b49881908916e7137f8b655c |
completed | March 8, 2026, 8:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad3179b0148190b69b16b5d2051ece |
completed | March 8, 2026, 8:21 a.m. |
Created at: March 4, 2026, 7:26 p.m.