Triple
T997760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sturt Highway |
E21532
|
entity |
| Predicate | hasRouteNumber |
P1864
|
FINISHED |
| Object |
A20
A20 is a major Australian highway route designation used for the Sturt Highway, an important east–west transport corridor.
|
E118258
|
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: A20 | Statement: [Sturt Highway, hasRouteNumber, A20]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: A20 Context triple: [Sturt Highway, hasRouteNumber, A20]
-
A.
A22
A22 is a major Portuguese motorway, commonly known as Via do Infante, that runs across the Algarve region in southern Portugal.
-
B.
A24
A24 is an independent entertainment company known for producing and distributing critically acclaimed and distinctive films and television series.
-
C.
A24
A24 is a major road designation used in several countries, typically referring to important regional or intercity routes.
-
D.
A2C
A2C (Advantage Actor-Critic) is a popular synchronous policy gradient reinforcement learning algorithm that combines value-based and policy-based methods to improve training stability and efficiency.
-
E.
A40
A40 is a major French motorway, also known as the "Autoroute Blanche," that connects Mâcon to the Mont Blanc region through the Jura and Alps.
- 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: A20 Triple: [Sturt Highway, hasRouteNumber, A20]
Generated description
A20 is a major Australian highway route designation used for the Sturt Highway, an important east–west transport corridor.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: A20 Target entity description: A20 is a major Australian highway route designation used for the Sturt Highway, an important east–west transport corridor.
-
A.
A22
A22 is a major Portuguese motorway, commonly known as Via do Infante, that runs across the Algarve region in southern Portugal.
-
B.
A24
A24 is an independent entertainment company known for producing and distributing critically acclaimed and distinctive films and television series.
-
C.
A24
A24 is a major road designation used in several countries, typically referring to important regional or intercity routes.
-
D.
A2C
A2C (Advantage Actor-Critic) is a popular synchronous policy gradient reinforcement learning algorithm that combines value-based and policy-based methods to improve training stability and efficiency.
-
E.
A40
A40 is a major French motorway, also known as the "Autoroute Blanche," that connects Mâcon to the Mont Blanc region through the Jura and Alps.
- 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_69a493c476b48190b41fc5e793171cc6 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4e0f0d081908b888c246d001786 |
completed | March 1, 2026, 9:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac2a18db488190bf7d604fe6a33b9e |
completed | March 7, 2026, 1:37 p.m. |
| NEDg | Description generation | batch_69ac2ab3df188190a70c46b276b562fe |
completed | March 7, 2026, 1:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac2b28e9dc8190bdf5642def2399c5 |
completed | March 7, 2026, 1:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.