Triple
T33651214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air China Building, Beijing |
E862102
|
entity |
| Predicate | headquartersOfFlagCarrier |
P17490
|
FINISHED |
| Object | Air China |
—
|
NE NERFINISHED |
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: Air China | Statement: [Air China Building, Beijing, headquartersOfFlagCarrier, Air China]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: headquartersOfFlagCarrier Context triple: [Air China Building, Beijing, headquartersOfFlagCarrier, Air China]
-
A.
isFlagCarrierCodeOf
Indicates that a given airline code serves as the official flag carrier designation for a particular country or territory.
-
B.
associatedAirlineHeadquarters
Indicates that an airline is connected to or based at a particular headquarters location.
-
C.
linkedAirlineHeadquartersLocation
Indicates that an airline’s headquarters is located in the specified place or facility.
-
D.
headquartersFor
chosen
Indicates that a location serves as the main administrative center or base of operations for an organization or entity.
-
E.
operatorHeadquartersAirport
Indicates that the specified airport serves as the primary headquarters location for the operator.
- 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_69f349840ba881908e3bfce536aeb92b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fb19063c81909466b329655c8583 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f96badb08190994442c2aba840b1 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:42 a.m.