Triple
T4447126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Union |
E96315
|
entity |
| Predicate | operatedRoute |
P18593
|
FINISHED |
| Object | Paris–Algiers |
E10377
|
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: Paris–Algiers | Statement: [Air Union, operatedRoute, Paris–Algiers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paris–Algiers Context triple: [Air Union, operatedRoute, Paris–Algiers]
-
A.
Algerasluis
Algerasluis is a lock complex in the Netherlands that regulates water levels and shipping traffic on the Hollandsche IJssel near Rotterdam.
-
B.
Algiers
chosen
Algiers is the capital and largest city of Algeria, a major political, economic, and cultural center on the Mediterranean coast of North Africa.
-
C.
Kasserine
Kasserine is a city in west-central Tunisia known for its role as a major center of protest and unrest during the Tunisian Revolution.
-
D.
Paris to Dakar
Paris to Dakar was the iconic transcontinental route of the early Dakar Rally, running from the French capital across Europe and the Sahara Desert to Senegal’s capital on the Atlantic coast.
-
E.
Ajdabiya
Ajdabiya is a strategic town in northeastern Libya that became a key battleground during the 2011 Libyan Civil War due to its location on major coastal and desert routes.
- 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_69b345415ba481908df738e7174448ba |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355d31e10819086590b9f828d50b0 |
completed | March 13, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b61386df48819080e44a23b9d67d23 |
completed | March 15, 2026, 2:03 a.m. |
Created at: March 12, 2026, 11:32 p.m.