Triple
T10342895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ali al-Akbar ibn Husayn |
E243668
|
entity |
| Predicate | roleInBattleOfKarbala |
P88789
|
FINISHED |
| Object | fought in Husayn ibn Ali’s small army |
—
|
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: fought in Husayn ibn Ali’s small army | Statement: [Ali al-Akbar ibn Husayn, roleInBattleOfKarbala, fought in Husayn ibn Ali’s small army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInBattleOfKarbala Context triple: [Ali al-Akbar ibn Husayn, roleInBattleOfKarbala, fought in Husayn ibn Ali’s small army]
-
A.
roleAtKarbala
chosen
Indicates the specific role, position, or function an entity held in relation to the events of the Battle of Karbala.
-
B.
sideInBattleOfBadr
Indicates the role or allegiance an entity had on a particular side during the Battle of Badr.
-
C.
roleInArabRevolt
Indicates that an entity played a specific role or had a particular involvement in the Arab Revolt.
-
D.
roleAtBattleOfUhud
Indicates the specific role, position, or function an entity held or performed during the Battle of Uhud.
-
E.
roleInLibyanCivilWar
Indicates the specific involvement, function, or position an entity had in the context of the Libyan Civil War.
- 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_69d381b22b8c8190aaed476be5f872a9 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e92105888190a08104deb9d0cf1c |
completed | April 7, 2026, 11:23 a.m. |
| PD | Predicate disambiguation | batch_69d4df9dc3208190bf1bd106f44f6202 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, 11:55 a.m.