Triple
T4474812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alice Hathaway Lee Roosevelt |
E98579
|
entity |
| Predicate | spouseDiaryNote |
P56759
|
FINISHED |
| Object | "The light has gone out of my life." |
—
|
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: "The light has gone out of my life." | Statement: [Alice Hathaway Lee Roosevelt, spouseDiaryNote, "The light has gone out of my life."]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseDiaryNote Context triple: [Alice Hathaway Lee Roosevelt, spouseDiaryNote, "The light has gone out of my life."]
-
A.
spouse
Indicates that two entities are married to each other in a legally or socially recognized partnership.
-
B.
spouseAction
Indicates that one person performs an action toward or on their spouse within the context of a marital relationship.
-
C.
spouseAssociatedWith
Indicates a marital or spousal relationship or close association between two entities.
-
D.
spouseNotableCommand
Indicates that the person’s spouse held a notable command position, such as leading a significant military unit, mission, or organization.
-
E.
hasSpouseInStory
Indicates that one entity is depicted as the spouse of another within the context of a particular story or narrative.
- 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_69b3454b4ae481908967426dd37284d6 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35728ed508190ba0e882fa62d8848 |
completed | March 13, 2026, 12:15 a.m. |
| PD | Predicate disambiguation | batch_69b3563d63008190816e37027e761375 |
completed | March 13, 2026, 12:11 a.m. |
| PDg | Predicate description generation | batch_69b35727a8ac819090420bd3e2cfbcf1 |
completed | March 13, 2026, 12:15 a.m. |
Created at: March 12, 2026, 11:35 p.m.