Triple
T17621569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cordelia Chase |
E429719
|
entity |
| Predicate | roleInAngelInvestigations |
P107060
|
FINISHED |
| Object | visionary link to The Powers That Be |
—
|
LITERAL FINISHED |
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: visionary link to The Powers That Be | Statement: [Cordelia Chase, roleInAngelInvestigations, visionary link to The Powers That Be]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInAngelInvestigations Context triple: [Cordelia Chase, roleInAngelInvestigations, visionary link to The Powers That Be]
-
A.
roleInBusinessVenture
Indicates that an entity holds a specific role or position within a particular business venture or entrepreneurial undertaking.
-
B.
roleInInvestigation
chosen
Indicates that an entity holds a specific function, capacity, or responsibility within the context of a particular investigation.
-
C.
typeOfInvestor
Indicates the kind or category of investor that a given entity is classified as.
-
D.
sharesAngel
Indicates that two entities have at least one angel investor in common.
-
E.
earlyInvestorIn
Indicates that one entity invested in another at an early stage of its development or funding lifecycle.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46db98c54819088dadec9f6bcc559 |
completed | April 19, 2026, 5:52 a.m. |
| PD | Predicate disambiguation | batch_69e3cdd7da34819099bc9481c5a79bab |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 5:51 a.m.