Triple
T31611003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MSCI USA Value Index |
E806624
|
entity |
| Predicate | hasTargetConstituents |
P74055
|
FINISHED |
| Object | U.S. large-cap companies |
—
|
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: U.S. large-cap companies | Statement: [MSCI USA Value Index, hasTargetConstituents, U.S. large-cap companies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTargetConstituents Context triple: [MSCI USA Value Index, hasTargetConstituents, U.S. large-cap companies]
-
A.
targetConstituents
chosen
Indicates that a larger entity is directed toward, affects, or is specifically intended for certain constituent parts or members within a whole.
-
B.
hasPrimaryConstituent
Indicates that one entity serves as the main or principal component, ingredient, or element of another entity.
-
C.
hasTarget
Indicates that one entity is directed toward, aimed at, or intended to affect another specific entity as its target.
-
D.
usesConstituentsFrom
Indicates that one entity is composed of, incorporates, or is derived from specific constituent parts provided by another entity.
-
E.
numberOfConstituents
Indicates the total count of individual components or members that make up a larger whole or group.
- 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_69f348d61f2081908cad94bc9ffbb671 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 30, 2026, 10:36 p.m.