Triple

T3936573
Position Surface form Disambiguated ID Type / Status
Subject Amman Citadel E90925 entity
Predicate ancientName P2834 FINISHED
Object Rabbath Ammon
Rabbath Ammon was the ancient capital of the Ammonite kingdom, located on the site of modern-day Amman in present-day Jordan.
 E398844 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: Rabbath Ammon | Statement: [Amman Citadel, ancientName, Rabbath Ammon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rabbath Ammon
Context triple: [Amman Citadel, ancientName, Rabbath Ammon]
  • A. Heshbon
    Heshbon is an ancient city in the Transjordan region frequently mentioned in the Bible as a significant Moabite and later Israelite center.
  • B. Riblah
    Riblah was an ancient town in Syria that served as a strategic military and administrative headquarters, notably used by the Babylonian king Nebuchadnezzar during the final conquest of Judah.
  • C. Kedesh
    Kedesh was an ancient city in the territory of the Israelite tribe of Naphtali, known as a Levitical city of refuge in the Hebrew Bible.
  • D. Erechim
    Erechim is a city in southern Brazil known for its strong German-Brazilian cultural heritage and influence.
  • E. Hamath
    Hamath is an ancient city of Syria, frequently mentioned in Near Eastern and biblical sources, located at the site of modern Hama on the Orontes River.
  • 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: Rabbath Ammon
Triple: [Amman Citadel, ancientName, Rabbath Ammon]
Generated description
Rabbath Ammon was the ancient capital of the Ammonite kingdom, located on the site of modern-day Amman in present-day Jordan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rabbath Ammon
Target entity description: Rabbath Ammon was the ancient capital of the Ammonite kingdom, located on the site of modern-day Amman in present-day Jordan.
  • A. Heshbon
    Heshbon is an ancient city in the Transjordan region frequently mentioned in the Bible as a significant Moabite and later Israelite center.
  • B. Riblah
    Riblah was an ancient town in Syria that served as a strategic military and administrative headquarters, notably used by the Babylonian king Nebuchadnezzar during the final conquest of Judah.
  • C. Kedesh
    Kedesh was an ancient city in the territory of the Israelite tribe of Naphtali, known as a Levitical city of refuge in the Hebrew Bible.
  • D. Erechim
    Erechim is a city in southern Brazil known for its strong German-Brazilian cultural heritage and influence.
  • E. Hamath
    Hamath is an ancient city of Syria, frequently mentioned in Near Eastern and biblical sources, located at the site of modern Hama on the Orontes River.
  • 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_69aed95f26e0819094b0e71974543a19 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeedceab608190934293d432f14476 completed March 9, 2026, 3:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5288eb3e481909a68531fd37371a4 completed March 14, 2026, 9:21 a.m.
NEDg Description generation batch_69b5297a08d08190a0150d71a795c66f completed March 14, 2026, 9:25 a.m.
NED2 Entity disambiguation (via description) batch_69b529d7a5a88190aa0728778e8540c5 completed March 14, 2026, 9:26 a.m.
Created at: March 9, 2026, 3:23 p.m.