Triple
T4674513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spandau Prison |
E103644
|
entity |
| Predicate | lastInmateCauseOfDeath |
P144
|
FINISHED |
| Object | suicide (official account) |
—
|
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: suicide (official account) | Statement: [Spandau Prison, lastInmateCauseOfDeath, suicide (official account)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastInmateCauseOfDeath Context triple: [Spandau Prison, lastInmateCauseOfDeath, suicide (official account)]
-
A.
diedInCustodyOf
Indicates that an individual died while under the control, supervision, or physical custody of a specified authority or entity.
-
B.
causeOfDeath
chosen
Indicates the specific factor, event, or condition that directly resulted in an entity’s death.
-
C.
reasonForDeath
Indicates the cause, circumstance, or condition that led to an entity’s death.
-
D.
deathCharacteristic
Indicates a characteristic, attribute, or quality specifically associated with a death event or the manner in which death occurred.
-
E.
allegedMannerOfDeath
Indicates that the specified manner of death is claimed or reported for an entity, but not confirmed as factual.
- 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_69bd43dda32c8190938b37744ca270fc |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd67c9c3c08190a6c4944cdd1362a8 |
completed | March 20, 2026, 3:29 p.m. |
| PD | Predicate disambiguation | batch_69bd6217e0088190836570522e324dc6 |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:15 p.m.