Triple
T16111900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aligarh district |
E390898
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Iglas |
E484335
|
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: Iglas | Statement: [Aligarh district, containsTown, Iglas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Iglas Context triple: [Aligarh district, containsTown, Iglas]
-
A.
Iglas
chosen
Iglas is a town in the Braj cultural region of northern India, known for its agrarian surroundings and local trading activities.
-
B.
Iglesiente
Iglesiente is a historical mining and coastal region in southwestern Sardinia, Italy, known for its rugged landscapes and rich mineral resources.
-
C.
Iglesia
Iglesia is a Madrid Metro station on Line 1 located in the Chamberí district, serving the area around the historic Iglesia de Santa Teresa y Santa Isabel.
-
D.
Basilika
Basilika is a comprehensive 9th-century Byzantine legal code that systematically revised and expanded Justinian’s laws into Greek.
-
E.
Direkli Church
Direkli Church is a rock-cut Byzantine cave church in Turkey’s Ihlara Valley, known for its early Christian frescoes and monastic heritage.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e20167ee1481909e56dc632bfc0fc5 |
completed | April 17, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeba90ffc81909d5eb8f0cfa9f147 |
completed | May 10, 2026, 2:21 a.m. |
Created at: April 10, 2026, 5 a.m.