Triple
T35927880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FTX |
E1039074
|
entity |
| Predicate | predecessorHeadquartersLocation |
P54261
|
FINISHED |
| Object | Hong Kong |
—
|
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: Hong Kong | Statement: [FTX, predecessorHeadquartersLocation, Hong Kong]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorHeadquartersLocation Context triple: [FTX, predecessorHeadquartersLocation, Hong Kong]
-
A.
headquartersPreviousLocation
chosen
Indicates that an entity’s headquarters used to be located at a specified place before moving to its current location.
-
B.
wasHeadquartersDuring
Indicates that a particular location served as the headquarters of an entity during a specified time period.
-
C.
issuerFormerHeadquartersCity
Indicates the city where the issuer’s former headquarters were located before moving or changing.
-
D.
predecessorCityName
Indicates that the value is the name of the city that previously held a given role, status, or position before the current city.
-
E.
headquartersFoundedAt
Indicates that an organization's headquarters was originally established at a specific location.
- 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_69f76e23e4688190a5369138755138bf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fddf721c1481909301a0f379368f10 |
completed | May 8, 2026, 1:04 p.m. |
| PD | Predicate disambiguation | batch_69fddda1ae7c8190b5848ff9a9e39826 |
completed | May 8, 2026, 12:57 p.m. |
Created at: May 3, 2026, 4:07 p.m.