Triple
T33816405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret Grubb |
E866690
|
entity |
| Predicate | startTime of marriage to John McDonald |
P201310
|
FINISHED |
| Object | after 1947 |
—
|
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: after 1947 | Statement: [Margaret Grubb, startTime of marriage to John McDonald, after 1947]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTime of marriage to John McDonald Context triple: [Margaret Grubb, startTime of marriage to John McDonald, after 1947]
-
A.
startTime (marriage to John Spencer-Churchill)
Indicates the date and time at which the marriage to John Spencer-Churchill began.
-
B.
marriageStartDateWithRobertCarr
Indicates the date on which an entity’s marriage to Robert Carr began.
-
C.
marriageToArgyllDate
Indicates the date on which the subject entered into marriage with the person titled Argyll.
-
D.
marriageToJoelMcAndrewStart
Indicates the time or event when an entity’s marriage to Joel McAndrew begins.
-
E.
marriageStartDateWithRobertDevereux
Indicates the date on which a marriage involving Robert Devereux officially began.
- 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_69f349911a8c81908478662194b23d8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ffe8ebe9fc8190b1934a3c4074370c |
completed | May 10, 2026, 2:09 a.m. |
| PD | Predicate disambiguation | batch_69ffe83a5de88190bed3e8bac86e8760 |
completed | May 10, 2026, 2:06 a.m. |
| PDg | Predicate description generation | batch_69ffe8eb47d48190acf7794ebe3ef4b8 |
completed | May 10, 2026, 2:09 a.m. |
Created at: May 1, 2026, 1:46 a.m.