Triple
T4196065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katherine |
E89155
|
entity |
| Predicate | servedByTrain |
P6301
|
FINISHED |
| Object | The Ghan |
E290594
|
NE 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: The Ghan | Statement: [Katherine, servedByTrain, The Ghan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Ghan Context triple: [Katherine, servedByTrain, The Ghan]
-
A.
The Ghan
chosen
The Ghan is a famous Australian long-distance passenger train that runs through the continent’s interior between Adelaide, Alice Springs, and Darwin.
-
B.
Takargo Rail
Takargo Rail is a Portuguese freight railway company that operates cargo transport services across the national rail network and into neighboring countries.
-
C.
Qantas Rising
Qantas Rising is an autobiographical book by Hudson Fysh recounting the early history and development of Qantas and Australian aviation.
-
D.
Serengeti Express
Serengeti Express is a scenic narrow-gauge railway attraction that transports guests through the African-themed savanna areas of Busch Gardens Tampa Bay.
-
E.
Kangaroo Bus
Kangaroo Bus is a hop-on, hop-off shuttle service that transports visitors around the San Diego Zoo’s main exhibits and attractions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69aed9569a4481908b6c1fcec2a11e21 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af035e87148190a0f0bf48b813ffaa |
completed | March 9, 2026, 5:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b58a0d7fa88190a2c830e298542068 |
completed | March 14, 2026, 4:17 p.m. |
Created at: March 9, 2026, 3:46 p.m.