Triple

T4472349
Position Surface form Disambiguated ID Type / Status
Subject Crusader states E98522 entity
Predicate capital P234 FINISHED
Object Tripoli E67268 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: Tripoli | Statement: [Crusader states, capital, Tripoli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tripoli
Context triple: [Crusader states, capital, Tripoli]
  • A. Tripoli
    Tripoli is a historic Mediterranean port city that serves as the capital and largest urban center of Libya.
  • B. Tripoli chosen
    Tripoli is Lebanon’s second-largest city, a historic Mediterranean port known for its medieval Mamluk architecture and vibrant commercial life.
  • C. Tripoli
    Tripoli is a historic city in the central Peloponnese of Greece that serves as the main urban and administrative center of the Arcadia region.
  • D. Misrata
    Misrata is a key coastal city in northwestern Libya, known as an important commercial and industrial hub and a strategic port on the Mediterranean Sea.
  • E. Sirte, Libya
    Sirte, Libya is a coastal city on the Mediterranean Sea that gained international prominence as Muammar Gaddafi’s final stronghold and the site of his death during the 2011 Libyan civil war.
  • 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_69b3454b4ae481908967426dd37284d6 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b356b832c0819096f76b694277d36e completed March 13, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69b66b33ecf48190a98ccbde9a3700c1 completed March 15, 2026, 8:17 a.m.
Created at: March 12, 2026, 11:35 p.m.