Triple
T13408495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tuz Khurmatu |
E320021
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Kifri |
E323952
|
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: Kifri | Statement: [Tuz Khurmatu, locatedNear, Kifri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kifri Context triple: [Tuz Khurmatu, locatedNear, Kifri]
-
A.
Kifri
chosen
Kifri is a town in Iraq with a significant Iraqi Turkmen population and cultural presence.
-
B.
Koufiya
Koufiya is an Arabic typeface designed by Nadine Chahine, known for its contemporary interpretation of traditional Kufic calligraphy.
-
C.
Khaf
Khaf is a city in northeastern Iran known for its location in Razavi Khorasan Province near the border with Afghanistan.
-
D.
Kurnub
Kurnub is an alternative name for Mamshit, an ancient Nabatean caravan town and archaeological site in the Negev Desert of Israel.
-
E.
Kfarhata
Kfarhata is a village located in the Koura District of northern Lebanon, known for its agricultural character and traditional rural setting.
- 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_69d806b943cc8190b6af624d385d7e12 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbae4d2c5481908facfaaa1501e344 |
completed | April 12, 2026, 2:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7307ad4448190b4fb99abcc00430b |
completed | May 3, 2026, 11:24 a.m. |
Created at: April 9, 2026, 9:35 p.m.