Triple
T3772210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Petra |
E83222
|
entity |
| Predicate | nearbyTown |
P3883
|
FINISHED |
| Object | Wadi Musa |
E385740
|
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: Wadi Musa | Statement: [Petra, nearbyTown, Wadi Musa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wadi Musa Context triple: [Petra, nearbyTown, Wadi Musa]
-
A.
Wadi Musa
chosen
Wadi Musa is a Jordanian town that serves as the main gateway and service hub for visitors to the ancient archaeological site of Petra.
-
B.
Wadi an-Nar
Wadi an-Nar is the Arabic name for the Kidron Valley’s seasonal watercourse that runs between Jerusalem and the Dead Sea.
-
C.
Wadi Hanifa
Wadi Hanifa is a major seasonal river valley in the Riyadh region of Saudi Arabia, known for its historical settlements, agricultural significance, and modern environmental rehabilitation as a scenic natural corridor.
-
D.
Wadi Fira
Wadi Fira is an administrative region in eastern Chad known for its arid Sahelian landscape and predominantly rural population.
-
E.
Wadi al-Joz
Wadi al-Joz is a predominantly Palestinian neighborhood in East Jerusalem known for its light industrial zone, auto-repair workshops, and proximity to the Old City.
- 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_69ad8b235e608190b5a2b1d1bfcef50b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc3219b881908a2f82126f9a679d |
completed | March 8, 2026, 7:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f039cd9c81908ea1428f2c328cdb |
completed | March 14, 2026, 5:20 a.m. |
Created at: March 8, 2026, 3:36 p.m.