Triple
T9075180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eannatum |
E217465
|
entity |
| Predicate | conflictWith |
P4897
|
FINISHED |
| Object | Umma |
E212533
|
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: Umma | Statement: [Eannatum, conflictWith, Umma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Umma Context triple: [Eannatum, conflictWith, Umma]
-
A.
Umma
chosen
Umma was an important Sumerian city-state in ancient Mesopotamia, known for its frequent territorial conflicts with the neighboring city-state of Lagash.
-
B.
Uarekena
Uarekena is an indigenous Arawakan language spoken by the Warekena people in parts of Brazil and Venezuela.
-
C.
Orile
Orile is a residential and commercial neighborhood located within the Surulere area of Lagos, Nigeria.
-
D.
Ikwuano
Ikwuano is a local government area in southeastern Nigeria known for its predominantly agrarian communities and cultural heritage within Abia State.
-
E.
Thunivu
Thunivu is a 2023 Tamil-language action heist film starring Ajith Kumar, known for its high-octane sequences and socially charged storyline.
- 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_69ca83d6c14c8190bc056d927f00a2a2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc95c4026c8190b553aedb9f4beabb |
completed | April 1, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cffdfe16c4819092c884bc3fe5daeb |
completed | April 3, 2026, 5:50 p.m. |
Created at: March 30, 2026, 7:12 p.m.