Triple
T924989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Magdalene |
E19963
|
entity |
| Predicate | firstWitnessOf |
P9232
|
FINISHED |
| Object | resurrected Jesus |
—
|
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: resurrected Jesus | Statement: [Mary Magdalene, firstWitnessOf, resurrected Jesus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstWitnessOf Context triple: [Mary Magdalene, firstWitnessOf, resurrected Jesus]
-
A.
notableWitness
chosen
Indicates that one entity is a significant or prominent witness to an event, action, or situation involving another entity.
-
B.
firstDemonstrated
Indicates that one entity was the earliest to show, prove, or exemplify a particular concept, method, or capability in relation to another entity or context.
-
C.
firstAccused
Indicates that the subject is the primary or earliest individual formally charged or blamed in a particular case or incident.
-
D.
firstOfficialClaimBy
Indicates that an entity is the earliest or original official source to assert or make a particular claim.
-
E.
firstAppeared
Indicates the earliest known time or context in which an entity was introduced, observed, or came into existence.
- 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_69a493a099788190a696d9d8408cbaf4 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b388f0bc8190a087222636135ba5 |
completed | March 1, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69a4b2970a4c8190b22cb2fd4706f62b |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.