Triple
T21235458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Global 2000 |
E523331
|
entity |
| Predicate | isRelatedTo |
P37
|
FINISHED |
| Object | Forbes Global 500 |
—
|
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: Forbes Global 500 | Statement: [Global 2000, isRelatedTo, Forbes Global 500]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Forbes Global 500 Context triple: [Global 2000, isRelatedTo, Forbes Global 500]
-
A.
Forbes Global 2000 list
chosen
The Forbes Global 2000 list is an annual ranking by Forbes magazine that identifies and ranks the world’s largest publicly traded companies based on a composite score of revenues, profits, assets, and market value.
-
B.
Fortune 500
Fortune 500 is an annual ranking by Fortune magazine that lists the 500 largest U.S. companies by total revenue.
-
C.
Fortune 1000
Fortune 1000 is an annual ranking by Fortune magazine that lists the 1,000 largest U.S. companies based on their revenues.
-
D.
Global 100
Global 100 is a ranking of the world’s largest and most prestigious law firms, typically ordered by metrics such as revenue and international reach.
-
E.
Fortune rankings
Fortune rankings are annual lists published by Fortune magazine that rank companies worldwide by various financial and performance metrics, such as revenue, profits, and market value.
- 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_69e0b513b89c81908b27147e91368db2 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7351f0e988190bb77b598cb8a9532 |
completed | April 21, 2026, 8:28 a.m. |
Created at: April 16, 2026, 3:46 p.m.