Triple
T11564308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shivta |
E274215
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Avdat |
E167528
|
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: Avdat | Statement: [Shivta, locatedNear, Avdat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Avdat Context triple: [Shivta, locatedNear, Avdat]
-
A.
Avdat National Park
chosen
Avdat National Park is an archaeological and nature reserve in Israel’s Negev Desert, centered on the ruins of the ancient Nabatean city of Avdat along the historic Incense Route.
-
B.
Tell ed-Duweir
Tell ed-Duweir is an archaeological site in Israel identified with the ancient city of Lachish, known for its rich remains from the Bronze and Iron Ages.
-
C.
Sumqayit
Sumqayit is a major industrial city on the Caspian Sea coast of Azerbaijan, known for its large chemical and metallurgical complexes.
-
D.
Tel Yarmuth
Tel Yarmuth is an important Bronze Age archaeological mound in central Israel, identified with the ancient Canaanite city of Yarmuth and known for its massive fortifications and palace complex.
-
E.
Tell al-Hiba
Tell al-Hiba is an important archaeological mound in southern Iraq identified with the ancient Sumerian city-state of Lagash.
- 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_69d6aae5ac3c81908d2b0a3a665665b2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88dd321f88190a57ecaf079fbbc3f |
completed | April 10, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e6e8b1a67481909a05105728acc358 |
completed | April 21, 2026, 3:02 a.m. |
Created at: April 8, 2026, 9:37 p.m.