Triple
T21805499
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WFC |
E538338
|
entity |
| Predicate | hasDataVendorCode |
P19199
|
FINISHED |
| Object | FactSet: WFC-US |
—
|
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: FactSet: WFC-US | Statement: [WFC, hasDataVendorCode, FactSet: WFC-US]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FactSet: WFC-US Context triple: [WFC, hasDataVendorCode, FactSet: WFC-US]
-
A.
FactSet
chosen
FactSet is a financial data and analytics platform widely used by investment professionals for market data, research, and portfolio analysis.
-
B.
WSFS
WSFS (World Science Fiction Society) is the international organization that oversees the World Science Fiction Convention and administers the Hugo Awards.
-
C.
FMP
FMP (Free Music Production) was a pioneering German independent record label known for its influential releases in free jazz and avant-garde improvised music.
-
D.
FMP
FMP is the commonly used acronym for the APEC Finance Ministers’ Process, a forum where Asia-Pacific economies coordinate regional financial and economic policy.
-
E.
WFC
WFC is a wide-field imaging instrument component commonly used in space- and ground-based telescopes to capture large areas of the sky in a single exposure.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f07802bffc8190b383a2c89de75f74 |
completed | April 28, 2026, 9:04 a.m. |
Created at: April 16, 2026, 6:53 p.m.