Triple
T16066703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret FitzGerald |
E389751
|
entity |
| Predicate | spouseGivenName |
P49524
|
FINISHED |
| Object | Wills |
E126897
|
NE 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: Wills | Statement: [Margaret FitzGerald, spouseGivenName, Wills]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wills Context triple: [Margaret FitzGerald, spouseGivenName, Wills]
-
A.
Wills
Wills is an Indian cigarette brand historically known for its prominent sponsorship of major cricket tournaments and events.
-
B.
Wills
chosen
Wills is a surname most notably associated with Childe Harold Wills, an early automotive engineer and key collaborator of Henry Ford in the development of the Model T.
-
C.
Will
Will is a common shortened form of the given name William, frequently used as a familiar or informal first name.
-
D.
Will
Will is a film or television production featuring actress Olivia DeJonge in its cast.
-
E.
Wills and Probate Registry
The Wills and Probate Registry is a specialized division of the DIFC Courts that oversees the registration and enforcement of wills and the administration of estates, particularly for non-Muslim expatriates in Dubai.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1837ca628819081dfc439fe322d58 |
completed | April 17, 2026, 12:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe480d59c8190962ac596a872b5e0 |
completed | May 10, 2026, 1:50 a.m. |
Created at: April 10, 2026, 4:57 a.m.