Triple
T4320657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tunisair |
E96506
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | TU |
E82108
|
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: TU | Statement: [Tunisair, IATAcode, TU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TU Context triple: [Tunisair, IATAcode, TU]
-
A.
TU
TU is the common English abbreviation for Tohoku University, a leading national research university in Sendai, Japan.
-
B.
TU
chosen
TU is the international vehicle registration code assigned to Tunisia.
-
C.
Tu
The Tu are a Mongolic-speaking ethnic minority in northwestern China, known for their Tibetan Buddhist traditions and distinctive agrarian culture in Qinghai and Gansu provinces.
-
D.
TA
TA is a common abbreviation for the Territorial Army, a volunteer reserve force that supports a country's regular armed forces.
-
E.
TA
TA is the standard abbreviation for *Transforming Anthropology*, a peer-reviewed academic journal focusing on critical and innovative scholarship in anthropology.
- 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_69b345422aac81909ddbadae437d122e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35114ed2c8190949c5d8032d7b921 |
completed | March 12, 2026, 11:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5d08d70408190aca5793a480cf54f |
completed | March 14, 2026, 9:18 p.m. |
Created at: March 12, 2026, 11:12 p.m.