Triple
T525565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orly 1 |
E10908
|
entity |
| Predicate | isComponentOf |
P5722
|
FINISHED |
| Object | Orly 1-2-3-4 terminal complex |
E10908
|
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: Orly 1-2-3-4 terminal complex | Statement: [Orly 1, isComponentOf, Orly 1-2-3-4 terminal complex]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Orly 1-2-3-4 terminal complex Context triple: [Orly 1, isComponentOf, Orly 1-2-3-4 terminal complex]
-
A.
Orly 4
Orly 4 is one of the main passenger terminals at Paris Orly Airport, serving as a hub for various domestic and international flights.
-
B.
Orly 3
Orly 3 is one of the main passenger terminals at Paris Orly Airport, serving as a hub for check-in, boarding, and arrivals operations.
-
C.
Orly 2
Orly 2 is one of the main passenger terminals at Paris Orly Airport, serving as a hub for various domestic and international flights.
-
D.
Orly 1
chosen
Orly 1 is one of the passenger terminals at Paris Orly Airport, serving as a key facility for check-in, boarding, and arrivals operations.
-
E.
Orit
Orit is the traditional biblical canon of Ethiopian Jews, encompassing their sacred scriptures and guiding religious teachings.
- 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_69a2e84b16c4819088d284c47c3a7968 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1b7f448819087e5e7f3b37d7142 |
completed | Feb. 28, 2026, 1:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a4b23f97448190bd85a8c85d338039 |
completed | March 1, 2026, 9:40 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.