Triple
T30304089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FMC Corporation |
E770730
|
entity |
| Predicate | formerBusinessUnit |
P14354
|
FINISHED |
| Object | FMC Lithium |
—
|
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: FMC Lithium | Statement: [FMC Corporation, formerBusinessUnit, FMC Lithium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerBusinessUnit Context triple: [FMC Corporation, formerBusinessUnit, FMC Lithium]
-
A.
formerOrganization
Indicates that an entity was previously affiliated with or employed by a given organization, but is no longer associated with it.
-
B.
formerCoreBusiness
chosen
Indicates that an entity was previously the main or primary line of business for another entity but no longer holds that status.
-
C.
formerBusinessModel
Indicates that an entity previously operated under a particular business model, but no longer does so.
-
D.
formerProduct
Indicates that an entity was previously a product of another entity but is no longer in that role or status.
-
E.
formerManagingCompany
Indicates that one entity previously served as the managing company responsible for overseeing or operating another entity, but no longer holds that role.
- 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_69f224881b948190b8c4921b250a44a3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fedd5a5f4c8190acce88db56303703 |
completed | May 9, 2026, 7:08 a.m. |
| PD | Predicate disambiguation | batch_69fed910b31c8190ae837163d146738d |
completed | May 9, 2026, 6:49 a.m. |
Created at: April 29, 2026, 7:49 p.m.