Triple
T8641705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nabataean inscriptions |
E204666
|
entity |
| Predicate | geographicRegion |
P285
|
FINISHED |
| Object | Petra |
E83222
|
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: Petra | Statement: [Nabataean inscriptions, geographicRegion, Petra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Petra Context triple: [Nabataean inscriptions, geographicRegion, Petra]
-
A.
Petra
chosen
Petra is an ancient rock-cut city in southern Jordan renowned for its monumental sandstone architecture and role as the former capital of the Nabataean Kingdom.
-
B.
Hatra
Hatra is an ancient fortified city in northern Iraq, renowned for its well-preserved blend of Hellenistic and Parthian architecture and its role as a major religious and trading center in the early centuries CE.
-
C.
Daulis
Daulis was an ancient Greek city in the region of Phocis, known from classical sources and associated with various local myths and traditions.
-
D.
Anjar
Anjar is a historic town in Lebanon renowned for its well-preserved Umayyad-era archaeological site and distinctive urban layout.
-
E.
Anjar
Anjar is a historic town in the Kutch district of Gujarat, India, known for its traditional architecture and its devastation in the 2001 Gujarat earthquake.
- 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_69ca834ca1c88190a11ffb0200342fac |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4795b07081908bfc9ebf35a50f07 |
completed | March 31, 2026, 10:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebc3b1f508190978df29d995f494c |
completed | April 2, 2026, 6:58 p.m. |
Created at: March 30, 2026, 6:28 p.m.