Triple
T11433675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shinkiari |
E270949
|
entity |
| Predicate | roadConnection |
P385
|
FINISHED |
| Object | Thakot |
E912481
|
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: Thakot | Statement: [Shinkiari, roadConnection, Thakot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thakot Context triple: [Shinkiari, roadConnection, Thakot]
-
A.
Thakot
chosen
Thakot is a town in Pakistan’s Khyber Pakhtunkhwa province, situated along the Indus River and serving as a key junction on routes linking the northern mountainous regions with the rest of the country.
-
B.
Ratanapura
Ratanapura is the historical name of the Ava Kingdom, a prominent Burmese kingdom that ruled central Myanmar from the 14th to 16th centuries.
-
C.
Tharmada
Tharmada is a town in central Saudi Arabia where the Central Najdi dialect of Arabic is commonly spoken.
-
D.
Thakoon
Thakoon is a New York-based fashion label founded by designer Thakoon Panichgul, known for its modern, feminine ready-to-wear collections and innovative prints.
-
E.
Makha Bucha
Makha Bucha is a major Buddhist holy day, primarily observed in Thailand, commemorating the Buddha’s teachings and a historic gathering of his disciples.
- 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_69d6aadeef688190874bcecd88b3dd9b |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d806c485f481909dd3d9b0993f3faf |
completed | April 9, 2026, 8:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5d379f8d48190860a1ef98505c42e |
completed | April 20, 2026, 7:19 a.m. |
Created at: April 8, 2026, 9:35 p.m.