Triple
T17292404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zlatitsa |
E419816
|
entity |
| Predicate | hasNearbyTown |
P3883
|
FINISHED |
| Object |
Pirdop
Pirdop is a small industrial town in western Bulgaria, known for its copper smelting plant and location in the Zlatitsa–Pirdop valley of the Balkan Mountains.
|
E1260890
|
NE FINISHED |
How this triple was built (4 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: Pirdop | Statement: [Zlatitsa, hasNearbyTown, Pirdop]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pirdop Context triple: [Zlatitsa, hasNearbyTown, Pirdop]
-
A.
Pirde
Pirde is the Kurdish name for the town of Altun Kupri in northern Iraq, located between Erbil and Kirkuk.
-
B.
Pischa
Pischa is a mountain area and ski region near Davos in the Swiss Alps, known for its freeride terrain and winter sports opportunities.
-
C.
Piro
Piro is an alternate name for the Yine language, an indigenous Arawakan language spoken in Peru.
-
D.
Piro
Piro is a town in the Bhojpur district of Bihar, India, known as one of the district’s principal urban and commercial centers.
-
E.
Pachoras
Pachoras is the ancient name of Faras, a historic Nubian town in northern Sudan known for its important archaeological remains and Christian-era cathedral wall paintings.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Pirdop Triple: [Zlatitsa, hasNearbyTown, Pirdop]
Generated description
Pirdop is a small industrial town in western Bulgaria, known for its copper smelting plant and location in the Zlatitsa–Pirdop valley of the Balkan Mountains.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pirdop Target entity description: Pirdop is a small industrial town in western Bulgaria, known for its copper smelting plant and location in the Zlatitsa–Pirdop valley of the Balkan Mountains.
-
A.
Pirde
Pirde is the Kurdish name for the town of Altun Kupri in northern Iraq, located between Erbil and Kirkuk.
-
B.
Pischa
Pischa is a mountain area and ski region near Davos in the Swiss Alps, known for its freeride terrain and winter sports opportunities.
-
C.
Piro
Piro is a town in the Bhojpur district of Bihar, India, known as one of the district’s principal urban and commercial centers.
-
D.
Piro
Piro is an alternate name for the Yine language, an indigenous Arawakan language spoken in Peru.
-
E.
Pachoras
Pachoras is the ancient name of Faras, a historic Nubian town in northern Sudan known for its important archaeological remains and Christian-era cathedral wall paintings.
- F. None of above. chosen
Provenance (5 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e4378438508190924f732ad748b4d0 |
completed | April 19, 2026, 2:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a017959ffb0819099d70ed1541158ee |
completed | May 11, 2026, 6:38 a.m. |
| NEDg | Description generation | batch_6a017c9e99888190a99e3910c46d90c5 |
completed | May 11, 2026, 6:52 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a017d340b988190a468753604150bd3 |
completed | May 11, 2026, 6:54 a.m. |
Created at: April 10, 2026, 5:40 a.m.