Triple
T36174237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viscount Tewkesbury, Marquess of Basilwether |
E1046532
|
entity |
| Predicate | deathOfRelative |
P89259
|
FINISHED |
| Object | father killed in a hunting accident (backstory) |
—
|
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: father killed in a hunting accident (backstory) | Statement: [Viscount Tewkesbury, Marquess of Basilwether, deathOfRelative, father killed in a hunting accident (backstory)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deathOfRelative Context triple: [Viscount Tewkesbury, Marquess of Basilwether, deathOfRelative, father killed in a hunting accident (backstory)]
-
A.
motherDeath
Indicates that the mother of the referenced individual has died.
-
B.
diedShortlyBefore
Indicates that one entity’s death occurred a brief time before another specified event or entity’s death.
-
C.
fatherDiedIn
Indicates that the person's father died in the specified place or event.
-
D.
familyLossEvent
chosen
Indicates an event in which a person experiences the loss or death of a family member.
-
E.
onceDeceased
Indicates that an entity was previously dead at some point in time, regardless of its current state.
- 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_69f76e3c1b10819081fc7a807a71cf84 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c777e924819081a6634f549fe552 |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c475c58c8190a883554231e88c88 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:08 p.m.