Triple
T13378900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tobiah the Ammonite |
E319262
|
entity |
| Predicate | alliedWith |
P37
|
FINISHED |
| Object | Geshem the Arab |
E319263
|
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: Geshem the Arab | Statement: [Tobiah the Ammonite, alliedWith, Geshem the Arab]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geshem the Arab Context triple: [Tobiah the Ammonite, alliedWith, Geshem the Arab]
-
A.
Geshem the Arab
chosen
Geshem the Arab was a regional leader and adversary of Nehemiah who opposed the rebuilding of Jerusalem’s walls in the 5th century BCE.
-
B.
Jahsh ibn Ri’ab
Jahsh ibn Ri’ab was an early Arab from the Quraysh tribe known primarily as the father of Zaynab bint Jahsh, a wife of the Prophet Muhammad.
-
C.
Belqasim
Belqasim is a personal given name of Arabic origin, used primarily in North African and Middle Eastern cultures.
-
D.
Abu Lulu
Abu Lulu was a Persian slave and craftsman historically known for assassinating the second Rashidun caliph, Umar ibn al-Khattab, in Medina.
-
E.
Jaffar
Jaffar is the sinister vizier and main antagonist portrayed by Conrad Veidt in the 1940 fantasy film "The Thief of Bagdad."
- 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_69d806b886bc8190b676e7768b8e01c5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dadce56c6c8190adf4e19f6d1bc233 |
completed | April 11, 2026, 11:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7306c18d481908ebc8f802e474479 |
completed | May 3, 2026, 11:24 a.m. |
Created at: April 9, 2026, 9:33 p.m.