Triple
T6692006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ikrima ibn Abi Jahl |
E152648
|
entity |
| Predicate | statusInSira |
P72235
|
FINISHED |
| Object | Former enemy turned Companion |
—
|
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: Former enemy turned Companion | Statement: [Ikrima ibn Abi Jahl, statusInSira, Former enemy turned Companion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusInSira Context triple: [Ikrima ibn Abi Jahl, statusInSira, Former enemy turned Companion]
-
A.
status
Indicates the current condition, state, or standing of an entity within a given context.
-
B.
statusIndicates
Indicates that a particular status value conveys or reflects the current condition, state, or situation of an entity or process.
-
C.
statusModel
Indicates that an entity is associated with a particular status representation or status-handling model.
-
D.
statusInLogic
Indicates the logical status or role an entity holds within a formal reasoning or inference context.
-
E.
statusInIran
Indicates the legal, social, or political standing or condition of an entity specifically within the context of Iran.
- 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_69c6880687b08190805278b504d1c92c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6cd0fa5188190a23281cb09d98139 |
completed | March 27, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69c6ad0d3c1081908dadff7a6a054123 |
completed | March 27, 2026, 4:15 p.m. |
| PDg | Predicate description generation | batch_69c6cd0d939081908ede0bb6ce19f559 |
completed | March 27, 2026, 6:31 p.m. |
Created at: March 27, 2026, 2:05 p.m.