Triple
T7912758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Russell 1000 Value Index |
E183737
|
entity |
| Predicate | screeningBasis |
P79747
|
FINISHED |
| Object | fundamental characteristics |
—
|
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: fundamental characteristics | Statement: [Russell 1000 Value Index, screeningBasis, fundamental characteristics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screeningBasis Context triple: [Russell 1000 Value Index, screeningBasis, fundamental characteristics]
-
A.
screeningType
Indicates the specific method or category of screening applied in a screening process or evaluation.
-
B.
screeningOutcome
Indicates the result or decision produced by a screening or evaluation process applied to an entity.
-
C.
screeningVenue
Indicates the place or location where a screening (such as a film or event showing) takes place.
-
D.
hasScreened
Indicates that one entity has shown, displayed, or evaluated another entity, typically in the context of presenting media or conducting a review or check.
-
E.
typicalScreeningTime
Indicates the usual or standard amount of time allocated for a screening to take place.
- F. None of above. chosen
Provenance (4 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_69ca828dec0c81908b8f55a4dbbb53ff |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a7383cc819084eab19799209d2e |
completed | March 31, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69cae92f9498819085277879e59aa072 |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf7882b048190baa333af9f698590 |
completed | March 30, 2026, 10:22 p.m. |
Created at: March 30, 2026, 5:04 p.m.