Triple
T2307589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keturah |
E51875
|
entity |
| Predicate | timeRelativeToSarah |
P1936
|
FINISHED |
| Object | married to Abraham after Sarah’s death |
—
|
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: married to Abraham after Sarah’s death | Statement: [Keturah, timeRelativeToSarah, married to Abraham after Sarah’s death]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeRelativeToSarah Context triple: [Keturah, timeRelativeToSarah, married to Abraham after Sarah’s death]
-
A.
timeRelativeToBirth
Indicates the temporal position of an event or state relative to an entity’s birth (e.g., before, at, or after birth).
-
B.
timeEquivalentOf
Indicates that two temporal entities represent the same point in time or duration, possibly expressed in different formats or units.
-
C.
timeDescribedAs
Indicates that a specific time or temporal interval is characterized, labeled, or expressed using a particular description or representation.
-
D.
time
chosen
Indicates a temporal relationship specifying when an event occurs or how entities are ordered or related in time.
-
E.
timeExistence
Indicates the period or duration during which an entity exists or is valid.
- 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_69a88b0bb30c81908ded03b006d29387 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abce1f4f0c8190a714e4dcb8449f7e |
completed | March 7, 2026, 7:05 a.m. |
| PD | Predicate disambiguation | batch_69abc58ce2a081908ce2f0cadd92e9f8 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:49 p.m.