Triple
T8670134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Badr site |
E205773
|
entity |
| Predicate | dateOfKeyEventHijri |
P81485
|
FINISHED |
| Object | 17 Ramadan 2 AH |
—
|
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: 17 Ramadan 2 AH | Statement: [Battle of Badr site, dateOfKeyEventHijri, 17 Ramadan 2 AH]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfKeyEventHijri Context triple: [Battle of Badr site, dateOfKeyEventHijri, 17 Ramadan 2 AH]
-
A.
hasCalendarDateHijri
chosen
Indicates that an entity is associated with a specific date expressed in the Hijri (Islamic) calendar.
-
B.
hijriYear
Indicates the Hijri (Islamic lunar calendar) year associated with an event, date, or entity.
-
C.
birthDateHijri
Indicates the date on which an entity was born, expressed according to the Hijri (Islamic) calendar.
-
D.
dateInHebrewCalendar
Indicates that a specific date is expressed according to the Hebrew (Jewish) calendar system rather than another calendar.
-
E.
birthYearHijri
Indicates the year of an entity’s birth expressed in the Hijri (Islamic) calendar.
- 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_69ca83529a9c8190b5c075b4f14636ed |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4917cb9881909a73b74e54250613 |
completed | March 31, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69cc4564e018819081036722f3e42a71 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:31 p.m.