Triple
T34719116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dujail trial |
E1000861
|
entity |
| Predicate | presidingJudge |
P19462
|
FINISHED |
| Object |
Raouf Abdul Rahman
Raouf Abdul Rahman was an Iraqi judge best known for overseeing and sentencing Saddam Hussein in the Dujail trial.
|
E2117411
|
NE 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: Raouf Abdul Rahman | Statement: [Dujail trial, presidingJudge, Raouf Abdul Rahman]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Raouf Abdul Rahman Triple: [Dujail trial, presidingJudge, Raouf Abdul Rahman]
Generated description
Raouf Abdul Rahman was an Iraqi judge best known for overseeing and sentencing Saddam Hussein in the Dujail trial.
Provenance (5 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_69f76dad3f108190a280fd0a2f4ee89a |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f7799156408190bd87449e7a1ee3fb |
completed | May 3, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3786c071f08190bff5c5c7c5742c76 |
completed | June 21, 2026, 6:37 a.m. |
| NEDg | Description generation | batch_6a3795de70608190b524fb711b7bff70 |
completed | June 21, 2026, 7:42 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a379778438c8190898d1d9c96e532c7 |
completed | June 21, 2026, 7:49 a.m. |
Created at: May 3, 2026, 3:59 p.m.