Triple
T7805194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahathir Mohamad |
E180531
|
entity |
| Predicate | honorificPrefix |
P536
|
FINISHED |
| Object | Tun |
E465556
|
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: Tun | Statement: [Mahathir Mohamad, honorificPrefix, Tun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tun Context triple: [Mahathir Mohamad, honorificPrefix, Tun]
-
A.
Tun
chosen
Tun is the highest federal title of honor in Malaysia, bestowed by the Yang di-Pertuan Agong for extraordinary service to the nation.
-
B.
Tissi
Tissi is a small municipality in the Sardinia region of Italy, located in the province of Sassari.
-
C.
Tarmuwa
Tarmuwa is a local government area in northeastern Nigeria known for its predominantly rural communities within Yobe State.
-
D.
Takrur
Takrur was an early West African kingdom located in the Senegal River valley, known for its role in trans-Saharan trade and its early adoption of Islam.
-
E.
Soussa
Soussa is an alternative name for Sousse, a major historic port city on Tunisia’s eastern Mediterranean coast known for its medina and tourism.
- 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_69ca827e50cc8190a92a733577184938 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69caf63838b88190a085756db9ca25c4 |
completed | March 30, 2026, 10:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb14439c8081908331caf450462a0e |
completed | March 31, 2026, 12:24 a.m. |
Created at: March 30, 2026, 4:35 p.m.