Triple
T15111113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harkness family |
E360912
|
entity |
| Predicate | wealthRank |
P25601
|
FINISHED |
| Object | among richest American families of early 20th century |
—
|
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: among richest American families of early 20th century | Statement: [Harkness family, wealthRank, among richest American families of early 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wealthRank Context triple: [Harkness family, wealthRank, among richest American families of early 20th century]
-
A.
wealthRanking
chosen
Indicates the relative ordering of entities based on their level of wealth or financial resources.
-
B.
populationRank
Indicates the relative position of an entity in an ordered list based on the size of its population.
-
C.
adjustedWealthRanking
Indicates a comparative ordering of entities based on their wealth after applying specified adjustments or normalization factors.
-
D.
portRank
Indicates the relative importance or hierarchical ranking assigned to a port within a given system or context.
-
E.
frequencyRankInUnitedStates
Indicates the relative position of something in an ordered list based on how frequently it occurs within the United States.
- 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_69d85a0491ec8190830960be8fafb994 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0058c04f481909deeac0271d961b6 |
completed | April 15, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69deb96c1d9c81909351558ed97bc5b7 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:05 a.m.