Triple
T5430977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Why I Killed Gandhi |
E121487
|
entity |
| Predicate | timeOfStatement |
P54535
|
FINISHED |
| Object | 1948 |
—
|
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: 1948 | Statement: [Why I Killed Gandhi, timeOfStatement, 1948]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfStatement Context triple: [Why I Killed Gandhi, timeOfStatement, 1948]
-
A.
time
Indicates a temporal relationship specifying when an event occurs or how entities are ordered or related in time.
-
B.
timeDefinite
chosen
Indicates that the associated event or state occurs at a clearly specified, fixed point or interval in time.
-
C.
timeStatus
Indicates the temporal state or condition of an event or entity relative to a reference time (e.g., past, present, future, ongoing, or scheduled).
-
D.
timePeriod
Indicates the specific span or interval of time during which an event, state, or relationship occurs or is valid.
-
E.
timePeriodImplied
Indicates that a time period is inferred or implied by context rather than being explicitly specified.
- 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_69bd463c65f0819082ee6483ab4b466a |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd8911a7348190ad9378a248190f07 |
completed | March 20, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_69bd846b8bdc81909dcdc2a3084226f2 |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:06 p.m.