Triple
T3642103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie-Anne Pierrette Paulze |
E77211
|
entity |
| Predicate | spouseExecution |
P32864
|
FINISHED |
| Object | Antoine Lavoisier executed by guillotine in 1794 |
—
|
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: Antoine Lavoisier executed by guillotine in 1794 | Statement: [Marie-Anne Pierrette Paulze, spouseExecution, Antoine Lavoisier executed by guillotine in 1794]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseExecution Context triple: [Marie-Anne Pierrette Paulze, spouseExecution, Antoine Lavoisier executed by guillotine in 1794]
-
A.
spouseExecutionMethod
chosen
Indicates the method by which a person's spouse was executed.
-
B.
spouseExecutionYear
Indicates the calendar year in which a person's spouse was executed.
-
C.
spouseExecutionPlace
Indicates the place where a person's spouse was executed.
-
D.
exSpouse
Indicates that two people were formerly married to each other but are no longer spouses.
-
E.
spouseExecutionContext
Indicates that one entity is the spouse of another within a specific legal, temporal, or situational context in which that marital relationship is recognized or relevant.
- 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_69ad85de1b988190a45f8dbfebc806fc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc359a91481908aef1c022f45e55c |
completed | March 8, 2026, 6:43 p.m. |
| PD | Predicate disambiguation | batch_69adb8445b2c8190ab07f6ad4e010d0e |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.