Triple
T20251635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellen Lewis Herndon |
E498568
|
entity |
| Predicate | deathBeforeSpouseTookOfficeAs |
P139406
|
FINISHED |
| Object | President of the United States |
—
|
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: President of the United States | Statement: [Ellen Lewis Herndon, deathBeforeSpouseTookOfficeAs, President of the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deathBeforeSpouseTookOfficeAs Context triple: [Ellen Lewis Herndon, deathBeforeSpouseTookOfficeAs, President of the United States]
-
A.
spouseDateOfDeath
Indicates the date on which a person's spouse died.
-
B.
spouseDeath
Indicates that one person's spouse has died, marking the event of the spouse's death in relation to that person.
-
C.
spouseLaterOffice
Indicates that one person’s spouse held a particular office or position at a later time than the person in question.
-
D.
marriedToUntilDeathOfSpouse
Indicates a marital relationship that is intended to remain in effect until the death of one of the spouses.
-
E.
spouseStatusAfterDeath
Indicates the marital status or spousal relationship of a person after the death of their spouse.
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e673a8b8488190b344df7a65f59684 |
completed | April 20, 2026, 6:42 p.m. |
| PD | Predicate disambiguation | batch_69e55b1b23f88190bdcbe2f81dd226dd |
completed | April 19, 2026, 10:45 p.m. |
| PDg | Predicate description generation | batch_69e56702ad04819099c1c08f28d16809 |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 11, 2026, 11:41 p.m.