Triple
T31349131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dodie Levy-Fraser |
E799537
|
entity |
| Predicate | spouseOrderForMichaelLandon |
P4764
|
FINISHED |
| Object | first wife |
—
|
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: first wife | Statement: [Dodie Levy-Fraser, spouseOrderForMichaelLandon, first wife]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseOrderForMichaelLandon Context triple: [Dodie Levy-Fraser, spouseOrderForMichaelLandon, first wife]
-
A.
spouseOrderRelativeToJanetLeigh
Indicates the position or sequence of a person’s spouse relative to Janet Leigh’s spouses (e.g., earlier or later in marital order).
-
B.
spouseOrderRelativeToGeneRoddenberry
Indicates the position or sequence of a person among Gene Roddenberry’s spouses (e.g., first spouse, second spouse, etc.).
-
C.
marriageEndToMichaelLandon
Indicates that a marriage ended and Michael Landon was the spouse to whom the marriage ended.
-
D.
marriageOrderRelativeToJasonRobards
Indicates the position or sequence of a marriage in relation to Jason Robards’ own marriages (e.g., earlier, later, or specific ordinal order).
-
E.
spouseOrder
chosen
Indicates the position or sequence of a person among multiple spouses in a marital relationship.
- 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_69f224e51614819083141459a080e97c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fd44474ed48190ac372e4c88d762ed |
completed | May 8, 2026, 2:02 a.m. |
| PD | Predicate disambiguation | batch_69fd41ef28a48190a66959be5c964461 |
completed | May 8, 2026, 1:52 a.m. |
Created at: April 29, 2026, 9:17 p.m.