Triple
T30750497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Custis IV |
E782942
|
entity |
| Predicate | granddaughterInLaw |
P171094
|
FINISHED |
| Object | Martha Dandridge Custis Washington |
—
|
NE NERFINISHED |
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: Martha Dandridge Custis Washington | Statement: [John Custis IV, granddaughterInLaw, Martha Dandridge Custis Washington]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: granddaughterInLaw Context triple: [John Custis IV, granddaughterInLaw, Martha Dandridge Custis Washington]
-
A.
grandsonInLaw
Indicates a relationship where one person is the husband of another person's granddaughter.
-
B.
daughterInLaw
Indicates a relationship where one person is the wife of another person's child.
-
C.
motherInLaw
Indicates a relationship where one person is the mother of another person's spouse.
-
D.
grandparentInLawOf
Indicates that one person is the grandparent of another person’s spouse, or the spouse of another person’s grandparent.
-
E.
sonInLaw
Indicates that one person is the husband of another person's child.
- 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_69f224af8d8481908bea03890c5618be |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f698ad83a08190a6834056ccc3e3a4 |
completed | May 3, 2026, 12:37 a.m. |
| PD | Predicate disambiguation | batch_69f69664142c8190bc695501056b0236 |
completed | May 3, 2026, 12:27 a.m. |
| PDg | Predicate description generation | batch_69f697e92e2c8190bed50d5ba0981b64 |
completed | May 3, 2026, 12:33 a.m. |
Created at: April 29, 2026, 8:38 p.m.