Triple
T28136011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Immigrants series |
E714207
|
entity |
| Predicate | notableCharacterFamilyName |
P149002
|
FINISHED |
| Object |
Lavette family
The Lavette family is the central multigenerational clan whose struggles, ambitions, and relationships drive Howard Fast’s historical saga The Immigrants series.
|
E1804683
|
NE FINISHED |
How this triple was built (3 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: Lavette family | Statement: [The Immigrants series, notableCharacterFamilyName, Lavette family]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lavette family Triple: [The Immigrants series, notableCharacterFamilyName, Lavette family]
Generated description
The Lavette family is the central multigenerational clan whose struggles, ambitions, and relationships drive Howard Fast’s historical saga The Immigrants series.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableCharacterFamilyName Context triple: [The Immigrants series, notableCharacterFamilyName, Lavette family]
-
A.
notableFamilyNameOf
chosen
Indicates that a particular family name is notably or prominently associated with a given person or family entity.
-
B.
notableFamilyFor
Indicates that a family is particularly recognized or distinguished for a specific person, achievement, role, or characteristic.
-
C.
notableFamilyIn
Indicates that a person is notably associated with or belongs to a particular family within a given place or context.
-
D.
notableLeaderFamily
Indicates that a person belongs to the family of a notable or prominent leader.
-
E.
refersToNotableFamily
Indicates that an entity is associated with, or makes reference to, a specific well-known or historically significant family.
- F. None of above.
Provenance (6 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_69efd6af156c81908f50c2cd7db0e1ef |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_6a0082989e6c819099fea0e706332e37 |
completed | May 10, 2026, 1:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a15d79e3e44819083d92a5628abdbf9 |
completed | May 26, 2026, 5:25 p.m. |
| NEDg | Description generation | batch_6a15d94968e08190a70b9d0e359c28fb |
completed | May 26, 2026, 5:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a15d9c2a704819095e2c65e42d63a17 |
completed | May 26, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_6a0081ed6a1481908baf472876e28db9 |
completed | May 10, 2026, 1:02 p.m. |
Created at: April 27, 2026, 9:50 p.m.