Triple
T16241978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al-Waziriya campus |
E394269
|
entity |
| Predicate | district |
P2709
|
FINISHED |
| Object |
Waziriya
Waziriya is a district in Baghdad, Iraq, known for hosting the Al-Waziriya university campus and various educational and administrative institutions.
|
E1201938
|
NE FINISHED |
How this triple was built (4 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: Waziriya | Statement: [Al-Waziriya campus, district, Waziriya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waziriya Context triple: [Al-Waziriya campus, district, Waziriya]
-
A.
Barraki
Barraki are a group of villainous warlords from the Lego Bionicle storyline, known for their underwater, crustacean-inspired designs and role as major antagonists.
-
B.
Al-Walaja
Al-Walaja is a Palestinian village located near Bethlehem in the southern West Bank, known for its agricultural terraces and the impact of the Israeli separation barrier on its lands.
-
C.
Dar al-Maaref
Dar al-Maaref is an Egyptian publishing house known for issuing influential Arabic literary and cultural works.
-
D.
Dar al-Salam
Dar al-Salam is an Islamic publishing house known for producing and distributing classical and contemporary religious texts.
-
E.
Wazzu
Wazzu is a popular nickname for Washington State University, a public research university located in Pullman, Washington.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Waziriya Triple: [Al-Waziriya campus, district, Waziriya]
Generated description
Waziriya is a district in Baghdad, Iraq, known for hosting the Al-Waziriya university campus and various educational and administrative institutions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Waziriya Target entity description: Waziriya is a district in Baghdad, Iraq, known for hosting the Al-Waziriya university campus and various educational and administrative institutions.
-
A.
Barraki
Barraki are a group of villainous warlords from the Lego Bionicle storyline, known for their underwater, crustacean-inspired designs and role as major antagonists.
-
B.
Al-Walaja
Al-Walaja is a Palestinian village located near Bethlehem in the southern West Bank, known for its agricultural terraces and the impact of the Israeli separation barrier on its lands.
-
C.
Dar al-Maaref
Dar al-Maaref is an Egyptian publishing house known for issuing influential Arabic literary and cultural works.
-
D.
Dar al-Salam
Dar al-Salam is an Islamic publishing house known for producing and distributing classical and contemporary religious texts.
-
E.
Wazzu
Wazzu is a popular nickname for Washington State University, a public research university located in Pullman, Washington.
- F. None of above. chosen
Provenance (5 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_69d87f2171208190951025e526947816 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2455eeb4c81909066a8af78329ef3 |
completed | April 17, 2026, 2:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000edf64a88190a9dd0c591c742977 |
completed | May 10, 2026, 4:51 a.m. |
| NEDg | Description generation | batch_6a00108174ac8190b3c421b115b7190e |
completed | May 10, 2026, 4:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0010f40d6081909927e8281ab17580 |
completed | May 10, 2026, 5 a.m. |
Created at: April 10, 2026, 5:04 a.m.