Triple
T11056276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Institution Narrative |
E261384
|
entity |
| Predicate | recounts |
P59712
|
FINISHED |
| Object | events of the Last Supper |
—
|
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: events of the Last Supper | Statement: [Institution Narrative, recounts, events of the Last Supper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recounts Context triple: [Institution Narrative, recounts, events of the Last Supper]
-
A.
recount
chosen
Indicates that an entity narrates or describes past events or experiences, often in a detailed or sequential manner, to another entity.
-
B.
recites
Indicates that one entity verbally delivers or repeats from memory the words, text, or performance associated with another entity.
-
C.
recall
Indicates that an entity retrieves or brings back into awareness information, events, or items that were previously known, experienced, or stored.
-
D.
recurrence
Indicates that an event, condition, or state happens again or repeatedly over time, often after a period of absence or resolution.
-
E.
reconstructs
Indicates performing an action to rebuild, restore, or reassemble something from its parts, damage, or prior state.
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798a152b4819095b74a8996346077 |
completed | April 9, 2026, 12:16 p.m. |
| PD | Predicate disambiguation | batch_69d7440da46c8190a77380d5d747ac9c |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.