Triple
T15772267
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ziyarat |
E382389
|
entity |
| Predicate | timeOfPerformance |
P73837
|
FINISHED |
| Object | Arbaeen |
E312074
|
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: Arbaeen | Statement: [Ziyarat, timeOfPerformance, Arbaeen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arbaeen Context triple: [Ziyarat, timeOfPerformance, Arbaeen]
-
A.
Arbaeen
chosen
Arbaeen is a major Shia Muslim religious observance marking the end of the 40-day mourning period for the martyrdom of Husayn ibn Ali at the Battle of Karbala, commemorated by one of the world’s largest annual pilgrimages.
-
B.
Abarkuh
Abarkuh is a historic desert city in central Iran known for its ancient cypress tree and traditional mud-brick architecture.
-
C.
Hadiyya
Hadiyya is a Cushitic language spoken primarily by the Hadiya people in southern Ethiopia.
-
D.
Humera
Humera is a town in northwestern Ethiopia near the borders with Eritrea and Sudan, known for its strategic location and sesame production.
-
E.
Arba-ilu
Arba-ilu is an alternative ancient name for the city of Arbela, a historically significant Assyrian city in northern Mesopotamia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e051976d248190adddd3db9f758e22 |
completed | April 16, 2026, 3:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff877c5ae88190aeb500bb5f0d73f7 |
completed | May 9, 2026, 7:14 p.m. |
Created at: April 10, 2026, 4:47 a.m.