Triple
T4852423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamar |
E108446
|
entity |
| Predicate | responseOfDavid |
P59945
|
FINISHED |
| Object | David was very angry but did not punish Amnon |
—
|
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: David was very angry but did not punish Amnon | Statement: [Tamar, responseOfDavid, David was very angry but did not punish Amnon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: responseOfDavid Context triple: [Tamar, responseOfDavid, David was very angry but did not punish Amnon]
-
A.
JesusResponsePattern
Indicates the characteristic way Jesus typically responds in a given situation, including his manner, tone, or type of action taken.
-
B.
responseTool
Indicates a tool, method, or mechanism used to produce, deliver, or manage a response in a given context.
-
C.
responseFormula
Indicates that one entity’s reaction, reply, or outcome is expressed or encoded in a specific formula or structured representation.
-
D.
responseFrom
Indicates that one entity is the originator or source of a response directed to another entity or request.
-
E.
wasResponseTo
Indicates that one event, action, or communication occurred as a direct reply or reaction to a preceding event, action, or communication.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69bd6dda5e808190a26ec85e4499d8e4 |
completed | March 20, 2026, 3:55 p.m. |
Created at: March 20, 2026, 1:26 p.m.