Triple

T22423977
Position Surface form Disambiguated ID Type / Status
Subject Merneptah Stele E554320 entity
Predicate mentions P831 FINISHED
Object Ashkelon NE NERFINISHED

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: Ashkelon | Statement: [Merneptah Stele, mentions, Ashkelon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ashkelon
Context triple: [Merneptah Stele, mentions, Ashkelon]
  • A. Ashkelon chosen
    Ashkelon is an ancient coastal city in the southern Levant, historically significant as one of the principal cities of the Philistines.
  • B. Kiryat Ekron
    Kiryat Ekron is a small town in central Israel, located near the city of Rehovot and known for its mixed residential and agricultural character.
  • C. Sha'ar Yafo
    Sha'ar Yafo is the Hebrew name for Jaffa Gate, one of the main historic entrances to Jerusalem’s Old City.
  • D. Ekron
    Ekron was an ancient Philistine city-state in the southern Levant, known as one of the five major cities of the Philistine pentapolis.
  • E. Hazor
    Hazor was an important ancient Canaanite city-state in northern Israel, known as one of the largest and most influential urban centers in the Levant during the Bronze and Iron Ages.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4f2d0c819091aa3558ea2ee630 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15a2af620819083338127e78137dc completed April 29, 2026, 1:08 a.m.
Created at: April 16, 2026, 8:47 p.m.