Triple
T14146900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loews Corporation |
E350573
|
entity |
| Predicate | isDiversified |
P14738
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Loews Corporation, isDiversified, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isDiversified Context triple: [Loews Corporation, isDiversified, true]
-
A.
diversifiedIn
chosen
Indicates that an entity has expanded its involvement, investments, or activities across multiple different areas, sectors, or asset types.
-
B.
isNonDiversified
Indicates that an entity’s resources, investments, or activities are concentrated in a limited set of areas rather than being spread across a diverse range.
-
C.
hasInternalDiversity
Indicates that an entity contains multiple distinct types, elements, or subgroups within itself, rather than being uniform or homogeneous.
-
D.
sawDiversificationOf
Indicates that the subject experienced or witnessed a process in which something became more varied, diverse, or differentiated over time.
-
E.
isMostDiverseClassOf
Indicates that one class has the greatest diversity (e.g., in members, attributes, or types) compared to all other classes in a given set.
- 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_69d827865f608190b311820428ae027b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de612266248190a8591b646fe30ae6 |
completed | April 14, 2026, 3:45 p.m. |
| PD | Predicate disambiguation | batch_69de05b8434c81908c33b1b513463b12 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 12:54 a.m.