Triple
T23128974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arda-Mulissu |
E577114
|
entity |
| Predicate | reasonForLostTitle |
P41735
|
FINISHED |
| Object | Sennacherib’s decision to favor Esarhaddon |
—
|
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: Sennacherib’s decision to favor Esarhaddon | Statement: [Arda-Mulissu, reasonForLostTitle, Sennacherib’s decision to favor Esarhaddon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForLostTitle Context triple: [Arda-Mulissu, reasonForLostTitle, Sennacherib’s decision to favor Esarhaddon]
-
A.
placeOfTitleLoss
Indicates the location where an entity lost a previously held title or status.
-
B.
titleForfeited
Indicates that an entity has lost or been stripped of a title or formal designation it previously held.
-
C.
reasonForTitle
Indicates the justification, cause, or basis for assigning a particular title to an entity.
-
D.
reasonForLossOfSuccessionRights
chosen
Indicates the specific cause or circumstance that led to an individual losing their rights of succession.
-
E.
regainedTitleFrom
Indicates that an entity has recovered a previously held title or position from another entity who had taken or held it in the interim.
- 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_69e245f7b0e481909c473ff4e6a54e2c |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e857b40819081f9df03fff64d48 |
completed | April 29, 2026, 4:52 a.m. |
| PD | Predicate disambiguation | batch_69ef89f83b108190aaaa1db6221fc163 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4 p.m.