Triple
T4670485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Orient |
E102948
|
entity |
| Predicate | mergerRole |
P15102
|
FINISHED |
| Object | founding constituent of Air France |
—
|
LITERAL 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: founding constituent of Air France | Statement: [Air Orient, mergerRole, founding constituent of Air France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mergerRole Context triple: [Air Orient, mergerRole, founding constituent of Air France]
-
A.
mergerPartner
Indicates that two entities are involved as counterparties in a merger transaction with each other.
-
B.
mergerType
Indicates the specific kind or category of merger relationship that exists between the involved entities.
-
C.
mergerResult
chosen
Indicates that one or more entities have combined into a single entity, specifying the outcome or resulting entity of the merger.
-
D.
mergerLocation
Indicates the place or venue where a merger between entities occurs or is formally executed.
-
E.
mergedInstitutionRole
Indicates that an institutional role has been combined or consolidated with another role into a single, merged position or function.
- F. None of above.
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_69bd43d9cba4819086c1ab1c2d9d2133 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd655aceb081908100ffc0498fe183 |
completed | March 20, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69bd6215864c8190b50ba0f63ba87d0c |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:15 p.m.