Triple
T4852694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Absalom’s revenge on Amnon |
E108452
|
entity |
| Predicate | hasTimeGapFromTrigger |
P57350
|
FINISHED |
| Object | approximately two years after Tamar’s rape |
—
|
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: approximately two years after Tamar’s rape | Statement: [Absalom’s revenge on Amnon, hasTimeGapFromTrigger, approximately two years after Tamar’s rape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTimeGapFromTrigger Context triple: [Absalom’s revenge on Amnon, hasTimeGapFromTrigger, approximately two years after Tamar’s rape]
-
A.
hasClockSince
Indicates that an entity has possessed or maintained a clock continuously from a specified point in time onward.
-
B.
hasTimeStart
Indicates that an event, process, or state begins at a specific point in time.
-
C.
hasTimeOfAction
chosen
Indicates that an action is associated with a specific point or interval in time when it occurs.
-
D.
hasTimeDepth
Indicates that something possesses or spans a measurable extent of time, such as duration, historical depth, or temporal layering.
-
E.
isThirtyMinutesBehind
Indicates that one entity’s time, schedule, or clock is exactly thirty minutes earlier than another reference time.
- 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_69bd440a89548190a5f14ba6da6b97dc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ddd17d881909f7731ff2b460e83 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2557388190a2d15571bacd24f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:26 p.m.